Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1952 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.8957. Min Act: -0.1700
Data Index: 26049 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.8799. Min Act: -0.1700
Data Index: 2879608 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.8322. Min Act: -0.1700
Data Index: 4200507 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.8163. Min Act: -0.1700
Data Index: 8249000 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.8004. Min Act: -0.1700
Data Index: 2482264 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.8163. Min Act: -0.1700
Data Index: 1840608 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.7844. Min Act: -0.1700
Data Index: 5451781 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.8163. Min Act: -0.1700
Data Index: 962059 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.7526. Min Act: -0.1700
Data Index: 233993 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.7526. Min Act: -0.1700
Data Index: 1422933 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.7366. Min Act: -0.1700
Data Index: 1785991 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.7366. Min Act: -0.1700
Data Index: 96323 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.7366. Min Act: -0.1700
Data Index: 4457404 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.7206. Min Act: -0.1700
Data Index: 819234 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.7046. Min Act: -0.1700
Data Index: 2374860 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.7206. Min Act: -0.1700
Data Index: 7909912 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.6886. Min Act: -0.1700
Data Index: 3008332 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.6886. Min Act: -0.1700
Data Index: 7230182 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.7046. Min Act: -0.1700
Data Index: 952789 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8957. Min Range: -2.8957
Max Act: 2.7046. Min Act: -0.1700
Data Index: 7867547 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19