Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6105 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.8272. Min Act: -0.1700
Data Index: 5750890 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.7959. Min Act: -0.1700
Data Index: 6593649 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.7334. Min Act: -0.1700
Data Index: 1426754 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.7647. Min Act: -0.1700
Data Index: 4801927 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.5772. Min Act: -0.1700
Data Index: 1652153 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.5147. Min Act: -0.1700
Data Index: 3712601 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.4834. Min Act: -0.1700
Data Index: 2655845 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.4209. Min Act: -0.1700
Data Index: 4471695 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.4209. Min Act: -0.1700
Data Index: 3997453 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.4209. Min Act: -0.1700
Data Index: 3244300 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.3897. Min Act: -0.1700
Data Index: 8247780 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.3584. Min Act: -0.1700
Data Index: 5667587 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.3272. Min Act: -0.1700
Data Index: 4207403 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.2647. Min Act: -0.1700
Data Index: 8476219 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.2959. Min Act: -0.1700
Data Index: 7178923 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.2647. Min Act: -0.1700
Data Index: 1389868 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.2334. Min Act: -0.1700
Data Index: 1849385 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.2022. Min Act: -0.1700
Data Index: 2687813 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.2022. Min Act: -0.1700
Data Index: 2296257 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8272. Min Range: -6.8272
Max Act: 6.1397. Min Act: -0.1700
Data Index: 3800501 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19