Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.4863. Min Act: -0.1700
Data Index: 3945987 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.4238. Min Act: -0.1700
Data Index: 4705344 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.3926. Min Act: -0.1700
Data Index: 1130523 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.3926. Min Act: -0.1700
Data Index: 5639335 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.2988. Min Act: -0.1700
Data Index: 3461461 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.2988. Min Act: -0.1700
Data Index: 748169 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.2988. Min Act: -0.1700
Data Index: 1243188 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.2363. Min Act: -0.1700
Data Index: 1187263 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.2051. Min Act: -0.1700
Data Index: 4288398 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.1738. Min Act: -0.1700
Data Index: 3851878 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.1426. Min Act: -0.1700
Data Index: 8629267 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.2051. Min Act: -0.1700
Data Index: 3550465 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.1738. Min Act: -0.1700
Data Index: 593595 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.1426. Min Act: -0.1700
Data Index: 4388772 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.1426. Min Act: -0.1700
Data Index: 8615026 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.1426. Min Act: -0.1700
Data Index: 2369684 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.1113. Min Act: -0.1700
Data Index: 8294377 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.1113. Min Act: -0.1700
Data Index: 2170204 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.1113. Min Act: -0.1700
Data Index: 3299244 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4863. Min Range: -5.4863
Max Act: 5.0488. Min Act: -0.1700
Data Index: 4823076 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19