Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1808 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2566. Min Range: -6.2566
Max Act: 6.2566. Min Act: -0.1700
Data Index: 507698 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2566. Min Range: -6.2566
Max Act: 6.1941. Min Act: -0.1698
Data Index: 3916754 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2566. Min Range: -6.2566
Max Act: 6.1316. Min Act: -0.1700
Data Index: 2000865 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2566. Min Range: -6.2566
Max Act: 6.0691. Min Act: -0.1700
Data Index: 6831019 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2566. Min Range: -6.2566
Max Act: 6.0379. Min Act: -0.1700
Data Index: 7562571 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2566. Min Range: -6.2566
Max Act: 6.0691. Min Act: -0.1699
Data Index: 8287194 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2566. Min Range: -6.2566
Max Act: 6.0379. Min Act: -0.1700
Data Index: 6257254 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2566. Min Range: -6.2566
Max Act: 6.0066. Min Act: -0.1700
Data Index: 1717830 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2566. Min Range: -6.2566
Max Act: 6.0066. Min Act: -0.1700
Data Index: 7089527 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2566. Min Range: -6.2566
Max Act: 5.9754. Min Act: -0.1700
Data Index: 8252910 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2566. Min Range: -6.2566
Max Act: 5.9754. Min Act: -0.1700
Data Index: 267332 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2566. Min Range: -6.2566
Max Act: 5.9754. Min Act: -0.1700
Data Index: 356674 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2566. Min Range: -6.2566
Max Act: 5.9441. Min Act: -0.1700
Data Index: 2641202 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2566. Min Range: -6.2566
Max Act: 5.9441. Min Act: -0.1700
Data Index: 8368971 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2566. Min Range: -6.2566
Max Act: 5.9441. Min Act: -0.1700
Data Index: 497108 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2566. Min Range: -6.2566
Max Act: 5.9441. Min Act: -0.1700
Data Index: 5793500 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2566. Min Range: -6.2566
Max Act: 5.9441. Min Act: -0.1700
Data Index: 4467972 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2566. Min Range: -6.2566
Max Act: 5.9441. Min Act: -0.1700
Data Index: 2914360 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2566. Min Range: -6.2566
Max Act: 5.9129. Min Act: -0.1700
Data Index: 6075064 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2566. Min Range: -6.2566
Max Act: 5.9441. Min Act: -0.1700
Data Index: 6355241 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19