Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0319. Min Range: -6.0319
Max Act: 6.0319. Min Act: -0.1700
Data Index: 191228 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0319. Min Range: -6.0319
Max Act: 6.0007. Min Act: -0.1700
Data Index: 2712195 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.9694. Min Act: -0.1700
Data Index: 7401043 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.9382. Min Act: -0.1700
Data Index: 4858426 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.9382. Min Act: -0.1700
Data Index: 1801280 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.9382. Min Act: -0.1700
Data Index: 882517 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.8757. Min Act: -0.1700
Data Index: 586735 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.8444. Min Act: -0.1700
Data Index: 1966204 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.7507. Min Act: -0.1700
Data Index: 4018479 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.7507. Min Act: -0.1700
Data Index: 6021727 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.6882. Min Act: -0.1700
Data Index: 3461581 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.6882. Min Act: -0.1700
Data Index: 669240 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.6569. Min Act: -0.1700
Data Index: 7168522 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.6569. Min Act: -0.1700
Data Index: 1112934 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.6569. Min Act: -0.1700
Data Index: 6712868 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.6257. Min Act: -0.1700
Data Index: 5799377 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.6569. Min Act: -0.1700
Data Index: 4147459 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.6257. Min Act: -0.1700
Data Index: 7852140 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.5632. Min Act: -0.1700
Data Index: 4728493 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0319. Min Range: -6.0319
Max Act: 5.5632. Min Act: -0.1700
Data Index: 3417584 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19