Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 111 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5957. Min Act: -0.1700
Data Index: 173835 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5645. Min Act: -0.1700
Data Index: 173838 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5645. Min Act: -0.1700
Data Index: 6334526 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5332. Min Act: -0.1700
Data Index: 6334528 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5020. Min Act: -0.1700
Data Index: 6334532 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5332. Min Act: -0.1700
Data Index: 807409 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5020. Min Act: -0.1700
Data Index: 6334928 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5332. Min Act: -0.1700
Data Index: 2121787 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5332. Min Act: -0.1700
Data Index: 6334924 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5020. Min Act: -0.1700
Data Index: 6334926 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5020. Min Act: -0.1700
Data Index: 4201115 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 8458717 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5020. Min Act: -0.1700
Data Index: 4201113 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4395. Min Act: -0.1700
Data Index: 6979312 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 8492098 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 6979317 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 2121784 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 4201110 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4707. Min Act: -0.1700
Data Index: 6334930 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4395. Min Act: -0.1700
Data Index: 3905572 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19