Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1542. Min Range: -3.1542
Max Act: 3.1542. Min Act: -0.1700
Data Index: 7520141 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1542. Min Range: -3.1542
Max Act: 3.1069. Min Act: -0.1700
Data Index: 3427505 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1542. Min Range: -3.1542
Max Act: 3.0911. Min Act: -0.1700
Data Index: 7520140 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1542. Min Range: -3.1542
Max Act: 3.0596. Min Act: -0.1693
Data Index: 7116144 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1542. Min Range: -3.1542
Max Act: 3.0596. Min Act: -0.1698
Data Index: 3371321 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1542. Min Range: -3.1542
Max Act: 3.0122. Min Act: -0.1700
Data Index: 7520156 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1542. Min Range: -3.1542
Max Act: 3.0122. Min Act: -0.1691
Data Index: 3409127 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1542. Min Range: -3.1542
Max Act: 3.0280. Min Act: -0.1700
Data Index: 7999514 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.9648. Min Act: -0.1700
Data Index: 7388322 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.9490. Min Act: -0.1691
Data Index: 6160093 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.9490. Min Act: -0.1699
Data Index: 7135434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.9490. Min Act: -0.1700
Data Index: 7418417 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.9490. Min Act: -0.1700
Data Index: 1009940 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.9173. Min Act: -0.1700
Data Index: 1130276 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.9015. Min Act: -0.1700
Data Index: 7520166 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.8697. Min Act: -0.1687
Data Index: 6160089 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.8856. Min Act: -0.1699
Data Index: 3380403 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.8538. Min Act: -0.1700
Data Index: 8293903 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.8697. Min Act: -0.1700
Data Index: 3746707 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1542. Min Range: -3.1542
Max Act: 2.8538. Min Act: -0.1700
Data Index: 3697838 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19