Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 132 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.5122. Min Act: -0.1700
Data Index: 760364 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.3559. Min Act: -0.1700
Data Index: 4210562 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.3247. Min Act: -0.1700
Data Index: 6880053 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.2622. Min Act: -0.1700
Data Index: 327233 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.1372. Min Act: -0.1700
Data Index: 579180 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.0747. Min Act: -0.1700
Data Index: 2420117 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.1059. Min Act: -0.1700
Data Index: 2684522 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.0747. Min Act: -0.1700
Data Index: 4578559 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.0747. Min Act: -0.1700
Data Index: 7924930 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.0434. Min Act: -0.1700
Data Index: 6588836 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.0122. Min Act: -0.1700
Data Index: 7242027 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5122. Min Range: -7.5122
Max Act: 7.0122. Min Act: -0.1700
Data Index: 5417345 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5122. Min Range: -7.5122
Max Act: 6.9809. Min Act: -0.1700
Data Index: 7575459 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5122. Min Range: -7.5122
Max Act: 6.9809. Min Act: -0.1700
Data Index: 798042 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5122. Min Range: -7.5122
Max Act: 6.9497. Min Act: -0.1700
Data Index: 8676339 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5122. Min Range: -7.5122
Max Act: 6.8872. Min Act: -0.1700
Data Index: 1677966 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5122. Min Range: -7.5122
Max Act: 6.9497. Min Act: -0.1700
Data Index: 5093366 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5122. Min Range: -7.5122
Max Act: 6.8559. Min Act: -0.1700
Data Index: 330729 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5122. Min Range: -7.5122
Max Act: 6.8559. Min Act: -0.1700
Data Index: 4972767 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5122. Min Range: -7.5122
Max Act: 6.8247. Min Act: -0.1700
Data Index: 3111871 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19