Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2851 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6749. Min Range: -8.6749
Max Act: 8.6749. Min Act: -0.1700
Data Index: 656721 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6749. Min Range: -8.6749
Max Act: 8.2999. Min Act: -0.1700
Data Index: 7194257 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6749. Min Range: -8.6749
Max Act: 8.1124. Min Act: -0.1700
Data Index: 8091569 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.7999. Min Act: -0.1700
Data Index: 6011778 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.6124. Min Act: -0.1700
Data Index: 6099192 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.6749. Min Act: -0.1700
Data Index: 3232594 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.6124. Min Act: -0.1700
Data Index: 3361541 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.6124. Min Act: -0.1700
Data Index: 6578909 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.5186. Min Act: -0.1700
Data Index: 3328086 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.5186. Min Act: -0.1700
Data Index: 5442926 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.4874. Min Act: -0.1700
Data Index: 3344997 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.4249. Min Act: -0.1700
Data Index: 736029 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.4249. Min Act: -0.1700
Data Index: 8822361 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.3624. Min Act: -0.1700
Data Index: 1383214 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.3624. Min Act: -0.1700
Data Index: 4762341 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.3624. Min Act: -0.1700
Data Index: 3591275 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.3936. Min Act: -0.1700
Data Index: 635041 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.3624. Min Act: -0.1700
Data Index: 1511188 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.3624. Min Act: -0.1700
Data Index: 7095515 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6749. Min Range: -8.6749
Max Act: 7.3311. Min Act: -0.1700
Data Index: 2493899 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19