Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4210 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3204. Min Range: -10.3204
Max Act: 10.3204. Min Act: -0.1700
Data Index: 4704826 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.9454. Min Act: -0.1700
Data Index: 7138493 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.6329. Min Act: -0.1700
Data Index: 2900283 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.5704. Min Act: -0.1700
Data Index: 4979136 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.4454. Min Act: -0.1700
Data Index: 8069739 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.4454. Min Act: -0.1700
Data Index: 5998223 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.3829. Min Act: -0.1700
Data Index: 1150579 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.3829. Min Act: -0.1700
Data Index: 900981 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.3829. Min Act: -0.1700
Data Index: 8384381 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.2579. Min Act: -0.1700
Data Index: 7533142 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.1954. Min Act: -0.1700
Data Index: 6977890 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.2579. Min Act: -0.1700
Data Index: 4868272 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.2579. Min Act: -0.1700
Data Index: 4764137 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.2579. Min Act: -0.1700
Data Index: 5955331 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.2579. Min Act: -0.1700
Data Index: 3009921 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.2579. Min Act: -0.1700
Data Index: 1324240 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.1954. Min Act: -0.1700
Data Index: 6049583 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.1954. Min Act: -0.1700
Data Index: 6485481 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.1954. Min Act: -0.1700
Data Index: 2927677 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3204. Min Range: -10.3204
Max Act: 9.1954. Min Act: -0.1700
Data Index: 1675295 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19