Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0003. Min Range: -3.0003
Max Act: 3.0003. Min Act: -0.1700
Data Index: 759477 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0003. Min Range: -3.0003
Max Act: 3.0003. Min Act: -0.1700
Data Index: 759480 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.9687. Min Act: -0.1700
Data Index: 7908318 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.9371. Min Act: -0.1700
Data Index: 759482 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.9371. Min Act: -0.1700
Data Index: 6486496 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.9212. Min Act: -0.1700
Data Index: 3424877 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.9054. Min Act: -0.1700
Data Index: 4453723 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.9054. Min Act: -0.1700
Data Index: 6340295 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.8736. Min Act: -0.1700
Data Index: 1942852 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.8578. Min Act: -0.1700
Data Index: 7339304 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.8419. Min Act: -0.1700
Data Index: 502442 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.8260. Min Act: -0.1700
Data Index: 6607723 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.8260. Min Act: -0.1700
Data Index: 6810372 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.8101. Min Act: -0.1700
Data Index: 6924915 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.8260. Min Act: -0.1700
Data Index: 1392740 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.8101. Min Act: -0.1700
Data Index: 7449980 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.8101. Min Act: -0.1700
Data Index: 6487502 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.8101. Min Act: -0.1700
Data Index: 7664318 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.8101. Min Act: -0.1700
Data Index: 1363132 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0003. Min Range: -3.0003
Max Act: 2.7941. Min Act: -0.1700
Data Index: 7334545 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19