Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2073 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.8678. Min Act: -0.1700
Data Index: 6927669 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.5553. Min Act: -0.1700
Data Index: 5858266 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.5553. Min Act: -0.1700
Data Index: 4892380 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.4303. Min Act: -0.1700
Data Index: 953662 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.4303. Min Act: -0.1700
Data Index: 7648602 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.3678. Min Act: -0.1700
Data Index: 4398504 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.3678. Min Act: -0.1700
Data Index: 8623486 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.3678. Min Act: -0.1700
Data Index: 6437728 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.2428. Min Act: -0.1700
Data Index: 6712341 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.2428. Min Act: -0.1700
Data Index: 260664 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.2428. Min Act: -0.1700
Data Index: 7299407 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.1803. Min Act: -0.1700
Data Index: 8346587 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.1178. Min Act: -0.1700
Data Index: 2116198 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.1803. Min Act: -0.1700
Data Index: 4629945 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.1178. Min Act: -0.1700
Data Index: 8813720 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.1178. Min Act: -0.1700
Data Index: 3692930 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.1178. Min Act: -0.1700
Data Index: 1023391 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.1178. Min Act: -0.1700
Data Index: 8527602 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.0553. Min Act: -0.1700
Data Index: 8553271 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8678. Min Range: -9.8678
Max Act: 9.0553. Min Act: -0.1700
Data Index: 2325464 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19