Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1581 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.8397. Min Act: -0.1700
Data Index: 51982 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.7772. Min Act: -0.1700
Data Index: 2227047 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.5272. Min Act: -0.1700
Data Index: 4030871 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.4647. Min Act: -0.1700
Data Index: 207360 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.4647. Min Act: -0.1700
Data Index: 2620455 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.4022. Min Act: -0.1700
Data Index: 3965736 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.3397. Min Act: -0.1700
Data Index: 529567 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.3397. Min Act: -0.1700
Data Index: 3453045 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.2772. Min Act: -0.1700
Data Index: 1395588 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.3397. Min Act: -0.1700
Data Index: 7946106 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.2772. Min Act: -0.1700
Data Index: 4899292 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.2147. Min Act: -0.1700
Data Index: 561875 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.2147. Min Act: -0.1700
Data Index: 3875775 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.2147. Min Act: -0.1700
Data Index: 6681943 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.2147. Min Act: -0.1700
Data Index: 6967856 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.1522. Min Act: -0.1700
Data Index: 6049057 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.1522. Min Act: -0.1700
Data Index: 1178891 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.1522. Min Act: -0.1700
Data Index: 39131 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.1522. Min Act: -0.1700
Data Index: 1136594 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8397. Min Range: -8.8397
Max Act: 8.0272. Min Act: -0.1700
Data Index: 2623222 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19