Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3708 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.9388. Min Act: -0.1700
Data Index: 7382750 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.7825. Min Act: -0.1700
Data Index: 3449245 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6888. Min Act: -0.1700
Data Index: 4271677 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.7200. Min Act: -0.1700
Data Index: 7561589 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6888. Min Act: -0.1700
Data Index: 2680240 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6888. Min Act: -0.1700
Data Index: 2882935 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6888. Min Act: -0.1700
Data Index: 2450317 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6575. Min Act: -0.1700
Data Index: 1379801 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6575. Min Act: -0.1700
Data Index: 951116 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6263. Min Act: -0.1700
Data Index: 5088339 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5950. Min Act: -0.1700
Data Index: 5795897 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5638. Min Act: -0.1700
Data Index: 5414468 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5638. Min Act: -0.1700
Data Index: 6299674 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5638. Min Act: -0.1700
Data Index: 6483733 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5325. Min Act: -0.1700
Data Index: 4682669 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5638. Min Act: -0.1700
Data Index: 8293396 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5013. Min Act: -0.1700
Data Index: 1188141 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5013. Min Act: -0.1700
Data Index: 4761268 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5013. Min Act: -0.1700
Data Index: 7196869 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5013. Min Act: -0.1700
Data Index: 5452204 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19