Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.5538. Min Act: -0.1700
Data Index: 7864856 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.3975. Min Act: -0.1700
Data Index: 3715779 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.3663. Min Act: -0.1700
Data Index: 2758056 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.3038. Min Act: -0.1700
Data Index: 3024851 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.2725. Min Act: -0.1700
Data Index: 540321 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.2725. Min Act: -0.1700
Data Index: 777233 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.2725. Min Act: -0.1700
Data Index: 4528810 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.2725. Min Act: -0.1700
Data Index: 1307011 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.1788. Min Act: -0.1700
Data Index: 3500997 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.1788. Min Act: -0.1700
Data Index: 3942707 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.1475. Min Act: -0.1700
Data Index: 944935 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.0850. Min Act: -0.1700
Data Index: 7395878 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.0850. Min Act: -0.1700
Data Index: 93191 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.0850. Min Act: -0.1700
Data Index: 5614379 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.0850. Min Act: -0.1700
Data Index: 8756915 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.0850. Min Act: -0.1700
Data Index: 8535445 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.0538. Min Act: -0.1700
Data Index: 8053502 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5538. Min Range: -7.5538
Max Act: 7.0538. Min Act: -0.1700
Data Index: 7119 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5538. Min Range: -7.5538
Max Act: 6.9913. Min Act: -0.1700
Data Index: 5830699 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5538. Min Range: -7.5538
Max Act: 6.9913. Min Act: -0.1700
Data Index: 1978174 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19