Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5751 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1520. Min Range: -9.1520
Max Act: 9.1520. Min Act: -0.1700
Data Index: 385307 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1520. Min Range: -9.1520
Max Act: 9.0270. Min Act: -0.1700
Data Index: 8034749 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.9645. Min Act: -0.1700
Data Index: 6948517 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.7770. Min Act: -0.1700
Data Index: 4177469 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.6520. Min Act: -0.1700
Data Index: 1742216 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.5270. Min Act: -0.1700
Data Index: 5954683 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.4645. Min Act: -0.1700
Data Index: 5050750 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.4645. Min Act: -0.1700
Data Index: 5567860 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.4020. Min Act: -0.1700
Data Index: 3313661 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.4020. Min Act: -0.1700
Data Index: 1448121 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.3395. Min Act: -0.1700
Data Index: 4149967 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.3395. Min Act: -0.1700
Data Index: 2526702 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.3395. Min Act: -0.1700
Data Index: 7217566 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.3395. Min Act: -0.1700
Data Index: 3048373 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.2770. Min Act: -0.1700
Data Index: 7256989 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.2770. Min Act: -0.1700
Data Index: 4014146 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.2145. Min Act: -0.1700
Data Index: 35039 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.2770. Min Act: -0.1700
Data Index: 7304851 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.1832. Min Act: -0.1700
Data Index: 4168839 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1520. Min Range: -9.1520
Max Act: 8.2145. Min Act: -0.1700
Data Index: 5602010 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19