Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3700 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.9857. Min Act: -0.1700
Data Index: 2536845 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.5169. Min Act: -0.1700
Data Index: 7077759 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.5169. Min Act: -0.1700
Data Index: 4278037 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.4857. Min Act: -0.1700
Data Index: 381822 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.4544. Min Act: -0.1700
Data Index: 6386941 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.4232. Min Act: -0.1700
Data Index: 1818758 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.4232. Min Act: -0.1700
Data Index: 110082 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.3919. Min Act: -0.1700
Data Index: 6234976 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.3919. Min Act: -0.1700
Data Index: 7135139 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.3919. Min Act: -0.1700
Data Index: 2599003 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.3607. Min Act: -0.1700
Data Index: 5911040 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.2982. Min Act: -0.1700
Data Index: 4489560 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.2982. Min Act: -0.1700
Data Index: 3238307 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.2982. Min Act: -0.1700
Data Index: 4989662 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.2982. Min Act: -0.1700
Data Index: 5929347 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.2669. Min Act: -0.1700
Data Index: 5288810 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.2669. Min Act: -0.1700
Data Index: 1630104 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.2357. Min Act: -0.1700
Data Index: 1336317 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.2357. Min Act: -0.1700
Data Index: 248064 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.2357. Min Act: -0.1700
Data Index: 3167661 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19