Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4520 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.9241. Min Act: -0.1700
Data Index: 3475252 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.8616. Min Act: -0.1700
Data Index: 7421404 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.8147. Min Act: -0.1700
Data Index: 133879 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.8147. Min Act: -0.1700
Data Index: 2291025 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7834. Min Act: -0.1700
Data Index: 6454773 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7990. Min Act: -0.1700
Data Index: 1769374 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7834. Min Act: -0.1700
Data Index: 8256456 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7990. Min Act: -0.1700
Data Index: 1497156 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7521. Min Act: -0.1700
Data Index: 6586251 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7521. Min Act: -0.1700
Data Index: 8705712 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7678. Min Act: -0.1700
Data Index: 6842270 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7521. Min Act: -0.1700
Data Index: 2435080 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7521. Min Act: -0.1700
Data Index: 4014590 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7521. Min Act: -0.1700
Data Index: 7999738 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7365. Min Act: -0.1700
Data Index: 7999737 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7208. Min Act: -0.1700
Data Index: 4364722 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7208. Min Act: -0.1700
Data Index: 3649232 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.6895. Min Act: -0.1700
Data Index: 840653 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7052. Min Act: -0.1700
Data Index: 7690854 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9241. Min Range: -3.9241
Max Act: 3.7052. Min Act: -0.1700
Data Index: 2442981 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19