Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2383 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.3377. Min Range: -12.3377
Max Act: 12.3377. Min Act: -0.1700
Data Index: 7013630 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3377. Min Range: -12.3377
Max Act: 11.2752. Min Act: -0.1700
Data Index: 782837 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3377. Min Range: -12.3377
Max Act: 11.2752. Min Act: -0.1700
Data Index: 6531794 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3377. Min Range: -12.3377
Max Act: 11.2127. Min Act: -0.1700
Data Index: 722997 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3377. Min Range: -12.3377
Max Act: 11.2127. Min Act: -0.1700
Data Index: 7472572 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3377. Min Range: -12.3377
Max Act: 11.2127. Min Act: -0.1700
Data Index: 4949276 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3377. Min Range: -12.3377
Max Act: 11.1502. Min Act: -0.1700
Data Index: 7730489 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3377. Min Range: -12.3377
Max Act: 11.0877. Min Act: -0.1700
Data Index: 3091645 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3377. Min Range: -12.3377
Max Act: 10.9002. Min Act: -0.1700
Data Index: 2486223 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3377. Min Range: -12.3377
Max Act: 11.0252. Min Act: -0.1700
Data Index: 2457207 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3377. Min Range: -12.3377
Max Act: 10.9627. Min Act: -0.1700
Data Index: 4949278 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3377. Min Range: -12.3377
Max Act: 10.9002. Min Act: -0.1700
Data Index: 5178175 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3377. Min Range: -12.3377
Max Act: 10.9002. Min Act: -0.1700
Data Index: 4316036 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3377. Min Range: -12.3377
Max Act: 10.8377. Min Act: -0.1700
Data Index: 4698998 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3377. Min Range: -12.3377
Max Act: 10.9002. Min Act: -0.1700
Data Index: 248158 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3377. Min Range: -12.3377
Max Act: 10.7127. Min Act: -0.1700
Data Index: 7486244 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3377. Min Range: -12.3377
Max Act: 10.7752. Min Act: -0.1700
Data Index: 2156761 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3377. Min Range: -12.3377
Max Act: 10.6502. Min Act: -0.1700
Data Index: 5674666 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3377. Min Range: -12.3377
Max Act: 10.4627. Min Act: -0.1700
Data Index: 2892426 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3377. Min Range: -12.3377
Max Act: 10.5252. Min Act: -0.1700
Data Index: 7687262 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19