Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.6524. Min Act: -0.1700
Data Index: 369466 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.6212. Min Act: -0.1700
Data Index: 4136885 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.6212. Min Act: -0.1700
Data Index: 8064630 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.5899. Min Act: -0.1700
Data Index: 4095552 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.5587. Min Act: -0.1700
Data Index: 5785646 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.5587. Min Act: -0.1700
Data Index: 6776507 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.5587. Min Act: -0.1700
Data Index: 1016001 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.5274. Min Act: -0.1700
Data Index: 6003801 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.5274. Min Act: -0.1700
Data Index: 1052463 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.5274. Min Act: -0.1700
Data Index: 2912790 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.5274. Min Act: -0.1700
Data Index: 3642690 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.4962. Min Act: -0.1700
Data Index: 3938964 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.4962. Min Act: -0.1699
Data Index: 3378700 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.4962. Min Act: -0.1700
Data Index: 3165698 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.4962. Min Act: -0.1700
Data Index: 162271 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.4962. Min Act: -0.1700
Data Index: 2701078 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.4962. Min Act: -0.1700
Data Index: 1270068 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.4649. Min Act: -0.1700
Data Index: 1830777 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.4649. Min Act: -0.1700
Data Index: 3727883 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6524. Min Range: -5.6524
Max Act: 5.4649. Min Act: -0.1700
Data Index: 631769 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19