Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.9370. Min Act: -0.1700
Data Index: 6561178 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.5932. Min Act: -0.1700
Data Index: 7842958 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.5932. Min Act: -0.1700
Data Index: 59934 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.4682. Min Act: -0.1700
Data Index: 4514604 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.4057. Min Act: -0.1700
Data Index: 1077525 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.4057. Min Act: -0.1700
Data Index: 2950107 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.3745. Min Act: -0.1700
Data Index: 6379600 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.3745. Min Act: -0.1700
Data Index: 6212263 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.2807. Min Act: -0.1700
Data Index: 2546292 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.3120. Min Act: -0.1700
Data Index: 5358729 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.3432. Min Act: -0.1700
Data Index: 1727277 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.2807. Min Act: -0.1700
Data Index: 6999522 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.2807. Min Act: -0.1700
Data Index: 7163324 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.2495. Min Act: -0.1700
Data Index: 514572 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.2182. Min Act: -0.1700
Data Index: 6048612 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.2495. Min Act: -0.1700
Data Index: 8344490 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.1870. Min Act: -0.1700
Data Index: 2395792 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.1870. Min Act: -0.1700
Data Index: 8062660 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.1557. Min Act: -0.1700
Data Index: 4465418 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9370. Min Range: -6.9370
Max Act: 6.1557. Min Act: -0.1700
Data Index: 6302501 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19