Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4826 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.5435. Min Act: -0.1700
Data Index: 582899 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.5123. Min Act: -0.1700
Data Index: 1221344 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.5123. Min Act: -0.1700
Data Index: 28235 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.5123. Min Act: -0.1700
Data Index: 5327258 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.5123. Min Act: -0.1700
Data Index: 5569130 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.4810. Min Act: -0.1700
Data Index: 5881396 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.4185. Min Act: -0.1700
Data Index: 5665492 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.4498. Min Act: -0.1700
Data Index: 404433 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3873. Min Act: -0.1700
Data Index: 1714794 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3873. Min Act: -0.1700
Data Index: 208008 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3873. Min Act: -0.1700
Data Index: 7113366 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3873. Min Act: -0.1700
Data Index: 7537740 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3873. Min Act: -0.1700
Data Index: 7581504 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3560. Min Act: -0.1700
Data Index: 2357432 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3560. Min Act: -0.1700
Data Index: 6101581 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3560. Min Act: -0.1700
Data Index: 4364812 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3248. Min Act: -0.1700
Data Index: 2953750 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3248. Min Act: -0.1700
Data Index: 5978107 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3248. Min Act: -0.1700
Data Index: 1960190 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5435. Min Range: -4.5435
Max Act: 4.3248. Min Act: -0.1700
Data Index: 8753692 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19