Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4720 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1555. Min Range: -7.1555
Max Act: 7.1555. Min Act: -0.1700
Data Index: 8330461 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.6868. Min Act: -0.1700
Data Index: 7070266 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.6868. Min Act: -0.1700
Data Index: 8210413 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.5305. Min Act: -0.1700
Data Index: 2272728 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.4993. Min Act: -0.1700
Data Index: 7534483 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.4368. Min Act: -0.1700
Data Index: 1748509 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.4055. Min Act: -0.1700
Data Index: 1654338 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.3743. Min Act: -0.1700
Data Index: 5087472 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.3430. Min Act: -0.1700
Data Index: 492665 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.3118. Min Act: -0.1700
Data Index: 105856 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.3430. Min Act: -0.1700
Data Index: 6502704 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.2493. Min Act: -0.1700
Data Index: 5793821 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.1868. Min Act: -0.1700
Data Index: 8628117 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.1555. Min Act: -0.1700
Data Index: 6542984 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.1555. Min Act: -0.1700
Data Index: 4199631 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.1555. Min Act: -0.1700
Data Index: 2266517 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.0930. Min Act: -0.1700
Data Index: 1170976 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.1243. Min Act: -0.1700
Data Index: 6594549 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.1243. Min Act: -0.1700
Data Index: 8155648 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1555. Min Range: -7.1555
Max Act: 6.1243. Min Act: -0.1700
Data Index: 2286313 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19