Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 382 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0379. Min Range: -5.0379
Max Act: 5.0379. Min Act: -0.1700
Data Index: 5121756 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0379. Min Range: -5.0379
Max Act: 5.0379. Min Act: -0.1700
Data Index: 5091471 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0379. Min Range: -5.0379
Max Act: 5.0379. Min Act: -0.1700
Data Index: 7121091 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0379. Min Range: -5.0379
Max Act: 5.0379. Min Act: -0.1700
Data Index: 545326 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0379. Min Range: -5.0379
Max Act: 5.0066. Min Act: -0.1700
Data Index: 7190833 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0379. Min Range: -5.0379
Max Act: 5.0066. Min Act: -0.1700
Data Index: 969463 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9754. Min Act: -0.1700
Data Index: 2590362 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9754. Min Act: -0.1700
Data Index: 3126712 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0379. Min Range: -5.0379
Max Act: 5.0066. Min Act: -0.1700
Data Index: 8654283 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9441. Min Act: -0.1700
Data Index: 4530722 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9441. Min Act: -0.1700
Data Index: 8283616 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9441. Min Act: -0.1700
Data Index: 7659650 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9754. Min Act: -0.1700
Data Index: 939029 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9754. Min Act: -0.1700
Data Index: 563684 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9441. Min Act: -0.1700
Data Index: 4322812 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9441. Min Act: -0.1700
Data Index: 2126370 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9441. Min Act: -0.1700
Data Index: 304489 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9441. Min Act: -0.1700
Data Index: 6937838 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9441. Min Act: -0.1700
Data Index: 1870970 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0379. Min Range: -5.0379
Max Act: 4.9441. Min Act: -0.1700
Data Index: 6875992 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19