Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.4933. Min Act: -0.1700
Data Index: 8676211 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.4933. Min Act: -0.1700
Data Index: 7533440 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.2746. Min Act: -0.1700
Data Index: 6359166 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.2121. Min Act: -0.1700
Data Index: 3582667 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.2433. Min Act: -0.1700
Data Index: 4787881 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.1808. Min Act: -0.1700
Data Index: 4610786 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.1183. Min Act: -0.1700
Data Index: 355925 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.1183. Min Act: -0.1700
Data Index: 8460453 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.0871. Min Act: -0.1700
Data Index: 3902660 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.0558. Min Act: -0.1700
Data Index: 757017 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.0558. Min Act: -0.1700
Data Index: 7442310 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4933. Min Range: -6.4933
Max Act: 5.9933. Min Act: -0.1700
Data Index: 1257529 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.0246. Min Act: -0.1700
Data Index: 1610591 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4933. Min Range: -6.4933
Max Act: 5.9933. Min Act: -0.1700
Data Index: 8439256 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4933. Min Range: -6.4933
Max Act: 5.9308. Min Act: -0.1700
Data Index: 3380602 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4933. Min Range: -6.4933
Max Act: 5.9308. Min Act: -0.1700
Data Index: 7144995 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4933. Min Range: -6.4933
Max Act: 5.9308. Min Act: -0.1700
Data Index: 6347953 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4933. Min Range: -6.4933
Max Act: 5.9308. Min Act: -0.1700
Data Index: 3066506 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4933. Min Range: -6.4933
Max Act: 5.9308. Min Act: -0.1700
Data Index: 1664131 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4933. Min Range: -6.4933
Max Act: 5.8683. Min Act: -0.1700
Data Index: 5903957 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19