Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.9913. Min Act: -0.1700
Data Index: 5352950 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.3975. Min Act: -0.1700
Data Index: 6676962 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.3350. Min Act: -0.1700
Data Index: 1985392 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.3350. Min Act: -0.1700
Data Index: 7195797 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.3350. Min Act: -0.1700
Data Index: 145671 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.3038. Min Act: -0.1700
Data Index: 5170290 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.2725. Min Act: -0.1700
Data Index: 7818234 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.2413. Min Act: -0.1700
Data Index: 6912524 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.2413. Min Act: -0.1700
Data Index: 1717968 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.2100. Min Act: -0.1700
Data Index: 320345 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.2100. Min Act: -0.1700
Data Index: 5742237 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.1788. Min Act: -0.1700
Data Index: 540787 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.1788. Min Act: -0.1700
Data Index: 8647272 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.1475. Min Act: -0.1700
Data Index: 1565518 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.1475. Min Act: -0.1700
Data Index: 3989310 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.1475. Min Act: -0.1700
Data Index: 7334452 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.1163. Min Act: -0.1700
Data Index: 3099571 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.1163. Min Act: -0.1700
Data Index: 8571601 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.1163. Min Act: -0.1700
Data Index: 247363 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9913. Min Range: -6.9913
Max Act: 6.1163. Min Act: -0.1700
Data Index: 8226404 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19