Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3349 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0339. Min Range: -7.0339
Max Act: 7.0339. Min Act: -0.1700
Data Index: 8339484 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.9401. Min Act: -0.1700
Data Index: 4006426 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.7839. Min Act: -0.1700
Data Index: 7102755 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.7839. Min Act: -0.1700
Data Index: 3313056 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.7526. Min Act: -0.1700
Data Index: 5990343 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.7214. Min Act: -0.1700
Data Index: 8651767 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.6901. Min Act: -0.1700
Data Index: 1334688 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.6901. Min Act: -0.1700
Data Index: 1470796 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.6276. Min Act: -0.1700
Data Index: 8812679 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.5964. Min Act: -0.1700
Data Index: 4926321 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.5651. Min Act: -0.1700
Data Index: 5210585 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.5339. Min Act: -0.1700
Data Index: 2466845 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.5026. Min Act: -0.1700
Data Index: 5064724 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.4714. Min Act: -0.1700
Data Index: 4822480 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.5026. Min Act: -0.1700
Data Index: 130489 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.5026. Min Act: -0.1700
Data Index: 8763444 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.5339. Min Act: -0.1700
Data Index: 3894676 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.4714. Min Act: -0.1700
Data Index: 7818210 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.4714. Min Act: -0.1700
Data Index: 988424 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0339. Min Range: -7.0339
Max Act: 6.4714. Min Act: -0.1700
Data Index: 7867572 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19