Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4351 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2196. Min Range: -6.2196
Max Act: 6.2196. Min Act: -0.1700
Data Index: 718989 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2196. Min Range: -6.2196
Max Act: 6.1259. Min Act: -0.1700
Data Index: 2750447 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2196. Min Range: -6.2196
Max Act: 6.0946. Min Act: -0.1700
Data Index: 3055328 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2196. Min Range: -6.2196
Max Act: 6.0634. Min Act: -0.1700
Data Index: 5958351 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2196. Min Range: -6.2196
Max Act: 6.0321. Min Act: -0.1700
Data Index: 2776030 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2196. Min Range: -6.2196
Max Act: 6.0321. Min Act: -0.1700
Data Index: 8666205 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2196. Min Range: -6.2196
Max Act: 6.0009. Min Act: -0.1700
Data Index: 2478648 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.9696. Min Act: -0.1700
Data Index: 1257511 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2196. Min Range: -6.2196
Max Act: 6.0009. Min Act: -0.1700
Data Index: 3130398 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.9696. Min Act: -0.1700
Data Index: 4054634 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.9384. Min Act: -0.1700
Data Index: 3634514 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.8759. Min Act: -0.1700
Data Index: 6916601 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.9384. Min Act: -0.1700
Data Index: 5239327 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.9071. Min Act: -0.1700
Data Index: 52419 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.8446. Min Act: -0.1700
Data Index: 4447408 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.9071. Min Act: -0.1700
Data Index: 1148422 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.8446. Min Act: -0.1700
Data Index: 5342788 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.8446. Min Act: -0.1700
Data Index: 8121443 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.8134. Min Act: -0.1700
Data Index: 7709679 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2196. Min Range: -6.2196
Max Act: 5.8134. Min Act: -0.1700
Data Index: 3197443 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19