Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 957 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.5524. Min Act: -0.1700
Data Index: 4773047 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.4587. Min Act: -0.1700
Data Index: 4899378 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.3962. Min Act: -0.1700
Data Index: 3396634 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.3337. Min Act: -0.1700
Data Index: 4992168 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.3337. Min Act: -0.1700
Data Index: 2988408 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.3024. Min Act: -0.1700
Data Index: 7978304 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2712. Min Act: -0.1700
Data Index: 7746909 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.3024. Min Act: -0.1700
Data Index: 650560 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2712. Min Act: -0.1700
Data Index: 2428375 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2712. Min Act: -0.1700
Data Index: 6249187 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2399. Min Act: -0.1700
Data Index: 2905420 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2399. Min Act: -0.1700
Data Index: 957506 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2399. Min Act: -0.1700
Data Index: 6412629 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2399. Min Act: -0.1700
Data Index: 3681243 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2087. Min Act: -0.1700
Data Index: 6373263 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2087. Min Act: -0.1700
Data Index: 8773364 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2399. Min Act: -0.1700
Data Index: 1696778 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2087. Min Act: -0.1700
Data Index: 4586177 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2087. Min Act: -0.1700
Data Index: 2905430 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5524. Min Range: -6.5524
Max Act: 6.2087. Min Act: -0.1700
Data Index: 6382084 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19