Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3171 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.5395. Min Act: -0.1700
Data Index: 5646949 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.4458. Min Act: -0.1700
Data Index: 1143506 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.4145. Min Act: -0.1700
Data Index: 6457275 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.2895. Min Act: -0.1700
Data Index: 51121 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.2583. Min Act: -0.1700
Data Index: 1358387 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.2270. Min Act: -0.1700
Data Index: 7973931 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.2270. Min Act: -0.1700
Data Index: 531977 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1958. Min Act: -0.1700
Data Index: 2070394 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1958. Min Act: -0.1700
Data Index: 8070108 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1958. Min Act: -0.1700
Data Index: 18570 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1958. Min Act: -0.1700
Data Index: 4982213 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1958. Min Act: -0.1700
Data Index: 6895496 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1958. Min Act: -0.1700
Data Index: 3023173 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1958. Min Act: -0.1700
Data Index: 6371882 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1645. Min Act: -0.1700
Data Index: 8431431 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1333. Min Act: -0.1700
Data Index: 7363754 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1333. Min Act: -0.1700
Data Index: 4474211 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1333. Min Act: -0.1700
Data Index: 664453 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1333. Min Act: -0.1700
Data Index: 7676529 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5395. Min Range: -5.5395
Max Act: 5.1333. Min Act: -0.1700
Data Index: 8255859 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19