Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.6402. Min Act: -0.1700
Data Index: 4776540 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5776. Min Act: -0.1700
Data Index: 7236146 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 6094833 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 4839165 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 7842588 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 7837498 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 2942292 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 7605167 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 4709583 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 4492812 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 2569144 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 7219320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 6315332 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 4227008 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 649915 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5462. Min Act: -0.1700
Data Index: 6081780 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5149. Min Act: -0.1700
Data Index: 2971632 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5149. Min Act: -0.1700
Data Index: 4777628 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5149. Min Act: -0.1700
Data Index: 3447087 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6402. Min Range: -3.6402
Max Act: 3.5149. Min Act: -0.1700
Data Index: 5037358 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19