Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2242 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2130. Min Range: -5.2130
Max Act: 5.2130. Min Act: -0.1700
Data Index: 8666221 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.9630. Min Act: -0.1700
Data Index: 5961384 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.8068. Min Act: -0.1700
Data Index: 1592524 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.7443. Min Act: -0.1700
Data Index: 773006 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.7443. Min Act: -0.1700
Data Index: 8439814 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.7130. Min Act: -0.1700
Data Index: 2663950 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.7130. Min Act: -0.1700
Data Index: 5922206 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.6818. Min Act: -0.1700
Data Index: 335638 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.7130. Min Act: -0.1700
Data Index: 3036038 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.6505. Min Act: -0.1700
Data Index: 505060 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.6818. Min Act: -0.1700
Data Index: 6336972 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.6818. Min Act: -0.1700
Data Index: 5633831 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.6505. Min Act: -0.1700
Data Index: 95695 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.6505. Min Act: -0.1700
Data Index: 1909682 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.6505. Min Act: -0.1700
Data Index: 635950 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.6193. Min Act: -0.1700
Data Index: 4053604 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.6505. Min Act: -0.1700
Data Index: 7626389 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.6193. Min Act: -0.1700
Data Index: 5465239 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.5568. Min Act: -0.1700
Data Index: 6824089 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.5568. Min Act: -0.1700
Data Index: 7693468 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19