Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 811 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.4308. Min Act: -0.1700
Data Index: 1296142 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.3683. Min Act: -0.1700
Data Index: 8133532 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.2120. Min Act: -0.1700
Data Index: 1323112 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.1495. Min Act: -0.1700
Data Index: 5032394 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.1495. Min Act: -0.1700
Data Index: 2501988 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.0870. Min Act: -0.1700
Data Index: 8423667 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.0558. Min Act: -0.1700
Data Index: 3187419 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9933. Min Act: -0.1700
Data Index: 3615122 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9308. Min Act: -0.1700
Data Index: 548918 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9308. Min Act: -0.1700
Data Index: 4850884 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.8995. Min Act: -0.1700
Data Index: 4319322 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.8995. Min Act: -0.1700
Data Index: 5649443 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.8683. Min Act: -0.1700
Data Index: 2376561 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.8683. Min Act: -0.1700
Data Index: 4910333 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.8995. Min Act: -0.1700
Data Index: 369955 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.8683. Min Act: -0.1700
Data Index: 3760296 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.8683. Min Act: -0.1700
Data Index: 2269209 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.8683. Min Act: -0.1700
Data Index: 2743239 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.8370. Min Act: -0.1700
Data Index: 6041189 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.8370. Min Act: -0.1700
Data Index: 8023698 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19