Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2598 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6527. Min Range: -7.6527
Max Act: 7.6527. Min Act: -0.1700
Data Index: 225937 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6527. Min Range: -7.6527
Max Act: 7.5589. Min Act: -0.1700
Data Index: 3684761 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6527. Min Range: -7.6527
Max Act: 7.4652. Min Act: -0.1700
Data Index: 3731119 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6527. Min Range: -7.6527
Max Act: 7.3089. Min Act: -0.1700
Data Index: 5355880 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6527. Min Range: -7.6527
Max Act: 7.2152. Min Act: -0.1700
Data Index: 6865736 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6527. Min Range: -7.6527
Max Act: 7.1527. Min Act: -0.1700
Data Index: 131019 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6527. Min Range: -7.6527
Max Act: 7.1527. Min Act: -0.1700
Data Index: 841769 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6527. Min Range: -7.6527
Max Act: 7.1214. Min Act: -0.1700
Data Index: 4038780 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9964. Min Act: -0.1700
Data Index: 393789 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9964. Min Act: -0.1700
Data Index: 1804270 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9652. Min Act: -0.1700
Data Index: 420832 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9652. Min Act: -0.1700
Data Index: 3418465 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9652. Min Act: -0.1700
Data Index: 3207590 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9339. Min Act: -0.1700
Data Index: 4608632 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9339. Min Act: -0.1700
Data Index: 1286199 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9339. Min Act: -0.1700
Data Index: 6111310 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9339. Min Act: -0.1700
Data Index: 1291607 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9027. Min Act: -0.1700
Data Index: 2155805 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9027. Min Act: -0.1700
Data Index: 3510635 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6527. Min Range: -7.6527
Max Act: 6.9027. Min Act: -0.1700
Data Index: 1834533 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19