Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 646 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4192. Min Range: -6.4192
Max Act: 6.4192. Min Act: -0.1700
Data Index: 1696835 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4192. Min Range: -6.4192
Max Act: 6.3880. Min Act: -0.1700
Data Index: 262635 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4192. Min Range: -6.4192
Max Act: 6.2942. Min Act: -0.1700
Data Index: 691145 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4192. Min Range: -6.4192
Max Act: 6.2005. Min Act: -0.1700
Data Index: 4566991 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4192. Min Range: -6.4192
Max Act: 6.1380. Min Act: -0.1700
Data Index: 8676677 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4192. Min Range: -6.4192
Max Act: 6.1067. Min Act: -0.1700
Data Index: 2949153 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4192. Min Range: -6.4192
Max Act: 6.0755. Min Act: -0.1700
Data Index: 1866172 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4192. Min Range: -6.4192
Max Act: 6.0442. Min Act: -0.1700
Data Index: 1377608 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4192. Min Range: -6.4192
Max Act: 5.9817. Min Act: -0.1700
Data Index: 173008 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4192. Min Range: -6.4192
Max Act: 6.0130. Min Act: -0.1700
Data Index: 2653272 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4192. Min Range: -6.4192
Max Act: 5.9192. Min Act: -0.1700
Data Index: 2681447 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4192. Min Range: -6.4192
Max Act: 5.9505. Min Act: -0.1700
Data Index: 3103329 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4192. Min Range: -6.4192
Max Act: 5.9192. Min Act: -0.1700
Data Index: 3046262 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4192. Min Range: -6.4192
Max Act: 5.9192. Min Act: -0.1700
Data Index: 1003849 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4192. Min Range: -6.4192
Max Act: 5.9192. Min Act: -0.1700
Data Index: 1707307 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4192. Min Range: -6.4192
Max Act: 5.9192. Min Act: -0.1700
Data Index: 7158833 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4192. Min Range: -6.4192
Max Act: 5.9192. Min Act: -0.1700
Data Index: 984626 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4192. Min Range: -6.4192
Max Act: 5.8567. Min Act: -0.1700
Data Index: 250437 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4192. Min Range: -6.4192
Max Act: 5.8880. Min Act: -0.1700
Data Index: 8219320 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4192. Min Range: -6.4192
Max Act: 5.8880. Min Act: -0.1700
Data Index: 6363365 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19