Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.8226. Min Act: -0.1700
Data Index: 8195984 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.7289. Min Act: -0.1700
Data Index: 366191 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.6664. Min Act: -0.1700
Data Index: 4734103 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.5101. Min Act: -0.1700
Data Index: 4803380 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.5101. Min Act: -0.1700
Data Index: 3747624 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.4789. Min Act: -0.1700
Data Index: 3011347 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.4789. Min Act: -0.1700
Data Index: 3725189 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.4476. Min Act: -0.1700
Data Index: 3889709 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.4476. Min Act: -0.1700
Data Index: 1272135 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.4164. Min Act: -0.1700
Data Index: 3217399 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.4164. Min Act: -0.1700
Data Index: 3993534 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.4164. Min Act: -0.1700
Data Index: 1786423 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.3851. Min Act: -0.1700
Data Index: 3926839 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.4164. Min Act: -0.1700
Data Index: 8304388 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.3851. Min Act: -0.1700
Data Index: 4241051 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.3539. Min Act: -0.1700
Data Index: 3417686 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.3539. Min Act: -0.1700
Data Index: 4586508 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.3539. Min Act: -0.1700
Data Index: 8078112 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.3539. Min Act: -0.1700
Data Index: 638865 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8226. Min Range: -5.8226
Max Act: 5.3539. Min Act: -0.1700
Data Index: 282130 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19