Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1506. Min Range: -5.1506
Max Act: 5.1506. Min Act: -0.1700
Data Index: 1448996 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.9631. Min Act: -0.1700
Data Index: 2747624 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.9318. Min Act: -0.1700
Data Index: 7314539 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.8381. Min Act: -0.1700
Data Index: 6266208 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.8381. Min Act: -0.1700
Data Index: 2446976 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.7443. Min Act: -0.1700
Data Index: 5618687 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.6818. Min Act: -0.1700
Data Index: 1055013 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.6818. Min Act: -0.1700
Data Index: 825026 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.6505. Min Act: -0.1700
Data Index: 113602 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.6505. Min Act: -0.1700
Data Index: 6849854 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.6505. Min Act: -0.1700
Data Index: 1216655 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.6193. Min Act: -0.1700
Data Index: 3571449 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.5880. Min Act: -0.1700
Data Index: 2433385 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.5880. Min Act: -0.1700
Data Index: 4378243 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.6193. Min Act: -0.1700
Data Index: 5123474 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.5880. Min Act: -0.1700
Data Index: 5592887 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.5880. Min Act: -0.1700
Data Index: 1775527 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.5255. Min Act: -0.1700
Data Index: 593108 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.5568. Min Act: -0.1700
Data Index: 5980068 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1506. Min Range: -5.1506
Max Act: 4.5568. Min Act: -0.1700
Data Index: 3815793 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19