Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2912 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3342. Min Range: -8.3342
Max Act: 8.3342. Min Act: -0.1700
Data Index: 2788562 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3342. Min Range: -8.3342
Max Act: 8.1467. Min Act: -0.1700
Data Index: 1383855 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.9592. Min Act: -0.1700
Data Index: 3230249 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.9592. Min Act: -0.1700
Data Index: 3859651 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.9280. Min Act: -0.1700
Data Index: 3230250 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.8967. Min Act: -0.1700
Data Index: 5015006 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.8967. Min Act: -0.1700
Data Index: 352928 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.8655. Min Act: -0.1700
Data Index: 1032933 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.8655. Min Act: -0.1700
Data Index: 6035104 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.8342. Min Act: -0.1700
Data Index: 7135180 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.8655. Min Act: -0.1700
Data Index: 1512210 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.8655. Min Act: -0.1700
Data Index: 2133026 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.8030. Min Act: -0.1700
Data Index: 3884688 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.7717. Min Act: -0.1700
Data Index: 4302386 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.7717. Min Act: -0.1700
Data Index: 7047042 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.7405. Min Act: -0.1700
Data Index: 4489765 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.7092. Min Act: -0.1700
Data Index: 8373081 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.7405. Min Act: -0.1700
Data Index: 6558598 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.6780. Min Act: -0.1700
Data Index: 3121998 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3342. Min Range: -8.3342
Max Act: 7.6467. Min Act: -0.1700
Data Index: 8049385 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19