Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4685 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5746. Min Range: -11.5746
Max Act: 11.5746. Min Act: -0.1700
Data Index: 2569431 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5746. Min Range: -11.5746
Max Act: 11.5121. Min Act: -0.1700
Data Index: 7729409 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5746. Min Range: -11.5746
Max Act: 11.4496. Min Act: -0.1700
Data Index: 2918121 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5746. Min Range: -11.5746
Max Act: 11.1371. Min Act: -0.1700
Data Index: 1106841 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5746. Min Range: -11.5746
Max Act: 11.0746. Min Act: -0.1700
Data Index: 6089953 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5746. Min Range: -11.5746
Max Act: 11.0746. Min Act: -0.1700
Data Index: 4007978 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5746. Min Range: -11.5746
Max Act: 11.0121. Min Act: -0.1700
Data Index: 1294444 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5746. Min Range: -11.5746
Max Act: 11.0121. Min Act: -0.1700
Data Index: 1914297 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.9496. Min Act: -0.1700
Data Index: 2337116 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.8246. Min Act: -0.1700
Data Index: 4638392 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.8246. Min Act: -0.1700
Data Index: 2136817 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.7621. Min Act: -0.1700
Data Index: 6174081 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.8246. Min Act: -0.1700
Data Index: 6434301 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.7621. Min Act: -0.1700
Data Index: 128327 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.6996. Min Act: -0.1700
Data Index: 7799866 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.6996. Min Act: -0.1700
Data Index: 7554652 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.6996. Min Act: -0.1700
Data Index: 3744875 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.6371. Min Act: -0.1700
Data Index: 6123681 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.6371. Min Act: -0.1700
Data Index: 3477476 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5746. Min Range: -11.5746
Max Act: 10.6371. Min Act: -0.1700
Data Index: 6622626 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19