Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0442. Min Range: -8.0442
Max Act: 8.0442. Min Act: -0.1700
Data Index: 7656721 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.7005. Min Act: -0.1700
Data Index: 5353438 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.5755. Min Act: -0.1700
Data Index: 2121965 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.4505. Min Act: -0.1700
Data Index: 7981387 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.4192. Min Act: -0.1700
Data Index: 707590 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.3880. Min Act: -0.1700
Data Index: 8127787 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.3880. Min Act: -0.1700
Data Index: 6831727 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.2317. Min Act: -0.1700
Data Index: 5588277 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.2005. Min Act: -0.1700
Data Index: 7048947 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.2317. Min Act: -0.1700
Data Index: 197482 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.1067. Min Act: -0.1700
Data Index: 733767 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.1380. Min Act: -0.1700
Data Index: 3613898 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.1380. Min Act: -0.1700
Data Index: 1991790 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.1067. Min Act: -0.1700
Data Index: 7312 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.1067. Min Act: -0.1700
Data Index: 4202744 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.0755. Min Act: -0.1700
Data Index: 45232 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.0755. Min Act: -0.1700
Data Index: 713710 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.0755. Min Act: -0.1700
Data Index: 5114511 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.0442. Min Act: -0.1700
Data Index: 49696 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0442. Min Range: -8.0442
Max Act: 7.0130. Min Act: -0.1700
Data Index: 457122 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19