Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2491 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.7927. Min Act: -0.1700
Data Index: 1284617 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.7302. Min Act: -0.1700
Data Index: 5240785 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.6989. Min Act: -0.1700
Data Index: 1336034 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.6364. Min Act: -0.1700
Data Index: 7880070 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.6364. Min Act: -0.1700
Data Index: 4124853 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.6364. Min Act: -0.1700
Data Index: 3749392 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.6364. Min Act: -0.1700
Data Index: 3953916 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.6364. Min Act: -0.1700
Data Index: 4803153 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.5739. Min Act: -0.1700
Data Index: 5941730 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.5427. Min Act: -0.1700
Data Index: 8292029 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.5427. Min Act: -0.1700
Data Index: 2408339 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.5427. Min Act: -0.1700
Data Index: 1067400 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.5427. Min Act: -0.1700
Data Index: 205196 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.4802. Min Act: -0.1700
Data Index: 5941733 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.5114. Min Act: -0.1700
Data Index: 1514084 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.5114. Min Act: -0.1700
Data Index: 8716484 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.5114. Min Act: -0.1700
Data Index: 1682770 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.5114. Min Act: -0.1700
Data Index: 824765 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.4802. Min Act: -0.1700
Data Index: 5553957 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7927. Min Range: -5.7927
Max Act: 5.5114. Min Act: -0.1700
Data Index: 755861 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19