Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5200 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0392. Min Range: -3.0392
Max Act: 3.0392. Min Act: -0.1700
Data Index: 3520003 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9918. Min Act: -0.1700
Data Index: 2173274 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9760. Min Act: -0.1700
Data Index: 8046225 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9760. Min Act: -0.1700
Data Index: 4943994 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9443. Min Act: -0.1700
Data Index: 359298 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9601. Min Act: -0.1700
Data Index: 2387130 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9443. Min Act: -0.1700
Data Index: 4992513 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9285. Min Act: -0.1700
Data Index: 8478631 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9285. Min Act: -0.1700
Data Index: 1958428 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9285. Min Act: -0.1700
Data Index: 3708589 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9126. Min Act: -0.1700
Data Index: 8370866 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9126. Min Act: -0.1700
Data Index: 4114526 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9126. Min Act: -0.1700
Data Index: 6833535 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9126. Min Act: -0.1700
Data Index: 5119163 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.9126. Min Act: -0.1700
Data Index: 6122839 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.8968. Min Act: -0.1700
Data Index: 2716390 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.8968. Min Act: -0.1700
Data Index: 5606824 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.8968. Min Act: -0.1700
Data Index: 3783582 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.8968. Min Act: -0.1700
Data Index: 4286039 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0392. Min Range: -3.0392
Max Act: 2.8968. Min Act: -0.1700
Data Index: 1705485 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19