Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1919 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1147. Min Range: -4.1147
Max Act: 4.1147. Min Act: -0.1700
Data Index: 2926173 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1147. Min Range: -4.1147
Max Act: 4.1147. Min Act: -0.1700
Data Index: 5141234 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1147. Min Range: -4.1147
Max Act: 4.0209. Min Act: -0.1700
Data Index: 6216471 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.9896. Min Act: -0.1700
Data Index: 2731160 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1147. Min Range: -4.1147
Max Act: 4.0053. Min Act: -0.1700
Data Index: 7570052 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.9740. Min Act: -0.1700
Data Index: 2696385 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.9740. Min Act: -0.1700
Data Index: 3478967 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.9896. Min Act: -0.1700
Data Index: 7030690 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.9115. Min Act: -0.1700
Data Index: 1352404 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.9271. Min Act: -0.1700
Data Index: 5570200 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.9115. Min Act: -0.1700
Data Index: 2755282 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.8958. Min Act: -0.1700
Data Index: 4011042 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.8958. Min Act: -0.1700
Data Index: 6060325 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.8802. Min Act: -0.1700
Data Index: 8628775 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.8646. Min Act: -0.1700
Data Index: 7084206 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.8646. Min Act: -0.1700
Data Index: 8558845 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.8333. Min Act: -0.1700
Data Index: 322210 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.8646. Min Act: -0.1700
Data Index: 326113 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.8646. Min Act: -0.1700
Data Index: 4804075 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1147. Min Range: -4.1147
Max Act: 3.8646. Min Act: -0.1700
Data Index: 5911591 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19