Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3174 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1289. Min Range: -6.1289
Max Act: 6.1289. Min Act: -0.1700
Data Index: 4732662 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1289. Min Range: -6.1289
Max Act: 6.0352. Min Act: -0.1700
Data Index: 4619516 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1289. Min Range: -6.1289
Max Act: 6.0352. Min Act: -0.1700
Data Index: 6827087 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1289. Min Range: -6.1289
Max Act: 6.0352. Min Act: -0.1700
Data Index: 6641358 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1289. Min Range: -6.1289
Max Act: 6.0352. Min Act: -0.1700
Data Index: 4607753 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1289. Min Range: -6.1289
Max Act: 6.0039. Min Act: -0.1700
Data Index: 4915133 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.9727. Min Act: -0.1700
Data Index: 6243136 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.9414. Min Act: -0.1700
Data Index: 8786474 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.9102. Min Act: -0.1700
Data Index: 6615451 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.9102. Min Act: -0.1700
Data Index: 4681141 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.8789. Min Act: -0.1700
Data Index: 8038784 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.8789. Min Act: -0.1700
Data Index: 2111004 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.8789. Min Act: -0.1700
Data Index: 4147139 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.8477. Min Act: -0.1700
Data Index: 3628316 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.8477. Min Act: -0.1700
Data Index: 3289889 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.8477. Min Act: -0.1700
Data Index: 7360006 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.8477. Min Act: -0.1700
Data Index: 3595722 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.7852. Min Act: -0.1700
Data Index: 1675694 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.8477. Min Act: -0.1700
Data Index: 4588673 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1289. Min Range: -6.1289
Max Act: 5.8164. Min Act: -0.1700
Data Index: 6801656 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19