Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2400 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.5520. Min Act: -0.1700
Data Index: 1424676 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.3645. Min Act: -0.1700
Data Index: 702255 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.3645. Min Act: -0.1700
Data Index: 2029842 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.3645. Min Act: -0.1700
Data Index: 1150910 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.3020. Min Act: -0.1700
Data Index: 3995567 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.3020. Min Act: -0.1700
Data Index: 7893426 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.3020. Min Act: -0.1700
Data Index: 2477751 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.2395. Min Act: -0.1700
Data Index: 6298563 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.2395. Min Act: -0.1700
Data Index: 2732058 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.2395. Min Act: -0.1700
Data Index: 967116 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.1770. Min Act: -0.1700
Data Index: 1782755 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.1770. Min Act: -0.1700
Data Index: 4883652 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.1770. Min Act: -0.1700
Data Index: 2381293 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.1770. Min Act: -0.1700
Data Index: 8683411 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.1770. Min Act: -0.1700
Data Index: 2689309 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.1770. Min Act: -0.1700
Data Index: 130409 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.1770. Min Act: -0.1700
Data Index: 887404 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.1770. Min Act: -0.1700
Data Index: 4400839 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.1145. Min Act: -0.1700
Data Index: 1879623 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5520. Min Range: -8.5520
Max Act: 8.1770. Min Act: -0.1700
Data Index: 5682762 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19