Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.7351. Min Act: -0.1700
Data Index: 4668886 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.4539. Min Act: -0.1700
Data Index: 5495584 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.4226. Min Act: -0.1700
Data Index: 3114786 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.2976. Min Act: -0.1700
Data Index: 4641707 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.2976. Min Act: -0.1700
Data Index: 7330295 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.2351. Min Act: -0.1700
Data Index: 8077672 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.2351. Min Act: -0.1700
Data Index: 1290394 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.1101. Min Act: -0.1700
Data Index: 3743060 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.0476. Min Act: -0.1700
Data Index: 2281482 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.0164. Min Act: -0.1700
Data Index: 5801143 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.0476. Min Act: -0.1700
Data Index: 7144299 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.0164. Min Act: -0.1700
Data Index: 2664046 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7351. Min Range: -6.7351
Max Act: 6.0164. Min Act: -0.1700
Data Index: 3446209 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7351. Min Range: -6.7351
Max Act: 5.9851. Min Act: -0.1700
Data Index: 7728507 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7351. Min Range: -6.7351
Max Act: 5.9851. Min Act: -0.1700
Data Index: 2532381 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7351. Min Range: -6.7351
Max Act: 5.9851. Min Act: -0.1700
Data Index: 7725411 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7351. Min Range: -6.7351
Max Act: 5.9851. Min Act: -0.1700
Data Index: 1587222 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7351. Min Range: -6.7351
Max Act: 5.9539. Min Act: -0.1700
Data Index: 767284 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7351. Min Range: -6.7351
Max Act: 5.9539. Min Act: -0.1700
Data Index: 1228076 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7351. Min Range: -6.7351
Max Act: 5.9851. Min Act: -0.1700
Data Index: 5163934 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19