Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4821 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.6763. Min Act: -0.1700
Data Index: 3982974 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.6138. Min Act: -0.1700
Data Index: 395916 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.6138. Min Act: -0.1700
Data Index: 8081524 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.6138. Min Act: -0.1700
Data Index: 1241377 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.5826. Min Act: -0.1700
Data Index: 8295899 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.5513. Min Act: -0.1700
Data Index: 1234498 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.5826. Min Act: -0.1700
Data Index: 1241374 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.5513. Min Act: -0.1700
Data Index: 3229650 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.5513. Min Act: -0.1700
Data Index: 1780641 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.5513. Min Act: -0.1700
Data Index: 1241369 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.5201. Min Act: -0.1700
Data Index: 1241367 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.4888. Min Act: -0.1700
Data Index: 3576119 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.4888. Min Act: -0.1700
Data Index: 1728820 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.4888. Min Act: -0.1700
Data Index: 3982971 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.4576. Min Act: -0.1700
Data Index: 3982970 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.4576. Min Act: -0.1700
Data Index: 2526290 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.4576. Min Act: -0.1700
Data Index: 5991542 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.4576. Min Act: -0.1700
Data Index: 5380443 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.4576. Min Act: -0.1700
Data Index: 4606247 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6763. Min Range: -5.6763
Max Act: 5.4263. Min Act: -0.1699
Data Index: 548957 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19