Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2105 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.1060. Min Act: -0.1700
Data Index: 4454264 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0920. Min Act: -0.1700
Data Index: 8627164 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0165. Min Act: -0.1700
Data Index: 1380695 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8818. Min Act: -0.1700
Data Index: 2687870 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8896. Min Act: -0.1700
Data Index: 1676594 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8874. Min Act: -0.1700
Data Index: 728194 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8889. Min Act: -0.1700
Data Index: 27706 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8408. Min Act: -0.1700
Data Index: 3566824 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8404. Min Act: -0.1700
Data Index: 7682581 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8404. Min Act: -0.1700
Data Index: 1889625 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8283. Min Act: -0.1700
Data Index: 910237 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8300. Min Act: -0.1700
Data Index: 8264943 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8296. Min Act: -0.1700
Data Index: 2026543 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8034. Min Act: -0.1700
Data Index: 5559026 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8044. Min Act: -0.1700
Data Index: 8256196 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8341. Min Act: -0.1700
Data Index: 6919080 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8465. Min Act: -0.1700
Data Index: 5710902 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8255. Min Act: -0.1700
Data Index: 8127866 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.7911. Min Act: -0.1700
Data Index: 1588707 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.7971. Min Act: -0.1700
Data Index: 4388125 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full textTruncated
Full Text #19