Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4355 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.6632. Min Act: -0.1700
Data Index: 6901149 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.6632. Min Act: -0.1700
Data Index: 1380798 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.6007. Min Act: -0.1700
Data Index: 6764070 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.6319. Min Act: -0.1700
Data Index: 900047 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.5382. Min Act: -0.1700
Data Index: 143883 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.5069. Min Act: -0.1700
Data Index: 7640755 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.5069. Min Act: -0.1700
Data Index: 4150528 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.5069. Min Act: -0.1700
Data Index: 8658041 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.5069. Min Act: -0.1700
Data Index: 7581064 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.5069. Min Act: -0.1700
Data Index: 1105510 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.4757. Min Act: -0.1700
Data Index: 2270622 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.4757. Min Act: -0.1700
Data Index: 1944544 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.4757. Min Act: -0.1700
Data Index: 1301737 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.4757. Min Act: -0.1700
Data Index: 8322421 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.4757. Min Act: -0.1700
Data Index: 2641585 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.4444. Min Act: -0.1700
Data Index: 1964986 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.4444. Min Act: -0.1700
Data Index: 5741125 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.4444. Min Act: -0.1700
Data Index: 5898425 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.4444. Min Act: -0.1700
Data Index: 3811903 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.3819. Min Act: -0.1700
Data Index: 2489482 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19