Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.8524. Min Act: -0.1700
Data Index: 7490594 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.6024. Min Act: -0.1700
Data Index: 6630504 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.6024. Min Act: -0.1700
Data Index: 7362520 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.5399. Min Act: -0.1700
Data Index: 6852996 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.2899. Min Act: -0.1700
Data Index: 3294299 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.2274. Min Act: -0.1700
Data Index: 4260879 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.2274. Min Act: -0.1700
Data Index: 182472 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.1649. Min Act: -0.1700
Data Index: 4803803 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.1024. Min Act: -0.1700
Data Index: 382227 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.1024. Min Act: -0.1700
Data Index: 7171097 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.0399. Min Act: -0.1700
Data Index: 5113479 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.1024. Min Act: -0.1700
Data Index: 1765022 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.0399. Min Act: -0.1700
Data Index: 884709 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.0399. Min Act: -0.1700
Data Index: 6511094 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8524. Min Range: -8.8524
Max Act: 8.0399. Min Act: -0.1700
Data Index: 8007131 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8524. Min Range: -8.8524
Max Act: 7.9774. Min Act: -0.1700
Data Index: 8303439 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8524. Min Range: -8.8524
Max Act: 7.9774. Min Act: -0.1700
Data Index: 166260 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8524. Min Range: -8.8524
Max Act: 7.9774. Min Act: -0.1700
Data Index: 6903209 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8524. Min Range: -8.8524
Max Act: 7.9774. Min Act: -0.1700
Data Index: 3757044 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8524. Min Range: -8.8524
Max Act: 7.9149. Min Act: -0.1700
Data Index: 1082883 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19