Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2493 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.4333. Min Act: -0.1700
Data Index: 3700416 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.3396. Min Act: -0.1700
Data Index: 2775088 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.2771. Min Act: -0.1700
Data Index: 4476455 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.2458. Min Act: -0.1700
Data Index: 2184994 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.2146. Min Act: -0.1700
Data Index: 1332317 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.1833. Min Act: -0.1700
Data Index: 7953491 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.1833. Min Act: -0.1700
Data Index: 2260463 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.1833. Min Act: -0.1700
Data Index: 6981160 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.1208. Min Act: -0.1700
Data Index: 4302365 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.1208. Min Act: -0.1700
Data Index: 7733470 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.1208. Min Act: -0.1700
Data Index: 1626960 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.0896. Min Act: -0.1700
Data Index: 8589236 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.1208. Min Act: -0.1700
Data Index: 1363852 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.0896. Min Act: -0.1700
Data Index: 1767757 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.0583. Min Act: -0.1700
Data Index: 6185914 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.0896. Min Act: -0.1700
Data Index: 8711354 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.0896. Min Act: -0.1700
Data Index: 5752157 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.0896. Min Act: -0.1700
Data Index: 7003251 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.0896. Min Act: -0.1700
Data Index: 7149937 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4333. Min Range: -7.4333
Max Act: 7.0583. Min Act: -0.1700
Data Index: 1317656 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19