Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0004. Min Range: -7.0004
Max Act: 7.0004. Min Act: -0.1700
Data Index: 6434604 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.8754. Min Act: -0.1700
Data Index: 8509745 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.7817. Min Act: -0.1700
Data Index: 266255 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.7504. Min Act: -0.1700
Data Index: 1522446 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.6567. Min Act: -0.1700
Data Index: 2289021 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.6879. Min Act: -0.1700
Data Index: 4756583 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.6567. Min Act: -0.1700
Data Index: 8285026 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.6254. Min Act: -0.1700
Data Index: 7331981 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.6567. Min Act: -0.1700
Data Index: 6879523 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.5942. Min Act: -0.1700
Data Index: 1853060 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.5629. Min Act: -0.1700
Data Index: 1924866 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.5004. Min Act: -0.1700
Data Index: 2968015 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.5317. Min Act: -0.1700
Data Index: 2908474 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.5004. Min Act: -0.1700
Data Index: 4979207 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.5004. Min Act: -0.1700
Data Index: 4904677 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.5317. Min Act: -0.1700
Data Index: 2502059 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.4692. Min Act: -0.1700
Data Index: 8763481 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.4067. Min Act: -0.1700
Data Index: 4204989 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.4067. Min Act: -0.1700
Data Index: 1683373 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0004. Min Range: -7.0004
Max Act: 6.4067. Min Act: -0.1700
Data Index: 4519478 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19