Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1630. Min Range: -8.1630
Max Act: 8.1630. Min Act: -0.1700
Data Index: 58476 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1630. Min Range: -8.1630
Max Act: 8.0380. Min Act: -0.1700
Data Index: 3431798 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.7880. Min Act: -0.1700
Data Index: 493410 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.7567. Min Act: -0.1700
Data Index: 5963428 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.6630. Min Act: -0.1700
Data Index: 457194 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.5380. Min Act: -0.1700
Data Index: 5922336 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.5067. Min Act: -0.1700
Data Index: 8724115 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.4442. Min Act: -0.1700
Data Index: 7646539 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.4130. Min Act: -0.1700
Data Index: 692307 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.3505. Min Act: -0.1700
Data Index: 472336 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.3192. Min Act: -0.1700
Data Index: 4005298 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.3505. Min Act: -0.1700
Data Index: 7386468 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.2880. Min Act: -0.1700
Data Index: 2489983 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.2880. Min Act: -0.1700
Data Index: 8558424 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.1942. Min Act: -0.1700
Data Index: 3478768 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.2567. Min Act: -0.1700
Data Index: 3752813 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.1942. Min Act: -0.1700
Data Index: 5981469 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.1630. Min Act: -0.1700
Data Index: 7473865 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.1630. Min Act: -0.1700
Data Index: 7242828 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1630. Min Range: -8.1630
Max Act: 7.1630. Min Act: -0.1700
Data Index: 7659125 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19