Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2696 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.6354. Min Act: -0.1700
Data Index: 7928159 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.4791. Min Act: -0.1700
Data Index: 2541717 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.4479. Min Act: -0.1700
Data Index: 1363010 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.4479. Min Act: -0.1700
Data Index: 4025978 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.4166. Min Act: -0.1700
Data Index: 4040993 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.3854. Min Act: -0.1700
Data Index: 4695269 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.3541. Min Act: -0.1699
Data Index: 3647460 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.3541. Min Act: -0.1700
Data Index: 6729952 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.3541. Min Act: -0.1700
Data Index: 6452488 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.3541. Min Act: -0.1700
Data Index: 3711160 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.3541. Min Act: -0.1700
Data Index: 5321738 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.3541. Min Act: -0.1700
Data Index: 5826242 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.3229. Min Act: -0.1700
Data Index: 1688537 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.2916. Min Act: -0.1700
Data Index: 3219824 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.3229. Min Act: -0.1700
Data Index: 6298226 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.3229. Min Act: -0.1700
Data Index: 4500388 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.2916. Min Act: -0.1700
Data Index: 6221733 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.2604. Min Act: -0.1700
Data Index: 4012302 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.3229. Min Act: -0.1700
Data Index: 5204349 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6354. Min Range: -5.6354
Max Act: 5.2916. Min Act: -0.1700
Data Index: 2358381 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19