Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4498 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.9485. Min Act: -0.1700
Data Index: 1639479 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.7610. Min Act: -0.1700
Data Index: 6617266 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.7610. Min Act: -0.1700
Data Index: 2299437 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.7610. Min Act: -0.1700
Data Index: 4599348 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.6985. Min Act: -0.1700
Data Index: 8274447 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.6673. Min Act: -0.1700
Data Index: 2939117 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.6360. Min Act: -0.1700
Data Index: 4253421 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.6048. Min Act: -0.1700
Data Index: 6881633 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.5735. Min Act: -0.1700
Data Index: 1464410 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.5423. Min Act: -0.1700
Data Index: 3340768 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.5423. Min Act: -0.1700
Data Index: 2138415 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.5110. Min Act: -0.1700
Data Index: 1776170 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.5110. Min Act: -0.1700
Data Index: 6997702 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.4798. Min Act: -0.1700
Data Index: 6498929 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.4485. Min Act: -0.1700
Data Index: 1457785 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.4173. Min Act: -0.1700
Data Index: 2724636 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.4173. Min Act: -0.1700
Data Index: 6221619 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.3860. Min Act: -0.1700
Data Index: 8224259 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.3860. Min Act: -0.1700
Data Index: 6452487 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9485. Min Range: -7.9485
Max Act: 7.3860. Min Act: -0.1700
Data Index: 550531 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19