Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 910 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.6594. Min Act: -0.1700
Data Index: 8530637 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.6438. Min Act: -0.1700
Data Index: 1120263 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.5812. Min Act: -0.1700
Data Index: 3006371 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.5655. Min Act: -0.1700
Data Index: 4288091 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.5499. Min Act: -0.1700
Data Index: 1661002 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.5342. Min Act: -0.1700
Data Index: 5639079 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.5186. Min Act: -0.1700
Data Index: 8668080 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.5029. Min Act: -0.1700
Data Index: 3632607 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.5186. Min Act: -0.1700
Data Index: 6660031 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.5029. Min Act: -0.1700
Data Index: 2781245 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.5029. Min Act: -0.1700
Data Index: 2455987 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.4872. Min Act: -0.1700
Data Index: 1199308 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.4716. Min Act: -0.1700
Data Index: 5765123 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.5029. Min Act: -0.1700
Data Index: 1928770 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.5029. Min Act: -0.1700
Data Index: 1108785 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.4872. Min Act: -0.1700
Data Index: 8269553 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.4559. Min Act: -0.1700
Data Index: 6827589 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.4559. Min Act: -0.1700
Data Index: 3880510 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.4716. Min Act: -0.1700
Data Index: 3433237 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6594. Min Range: -3.6594
Max Act: 3.4716. Min Act: -0.1700
Data Index: 365993 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19