Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4319 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5878. Min Range: -8.5878
Max Act: 8.5878. Min Act: -0.1700
Data Index: 6841757 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5878. Min Range: -8.5878
Max Act: 8.1190. Min Act: -0.1700
Data Index: 5260340 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.9315. Min Act: -0.1700
Data Index: 6942528 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.7440. Min Act: -0.1700
Data Index: 8681303 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.7440. Min Act: -0.1700
Data Index: 1233756 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.7128. Min Act: -0.1700
Data Index: 1998723 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.7440. Min Act: -0.1700
Data Index: 2622047 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.6190. Min Act: -0.1700
Data Index: 4755192 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.6503. Min Act: -0.1700
Data Index: 2150684 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.5878. Min Act: -0.1700
Data Index: 6803034 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.5565. Min Act: -0.1700
Data Index: 1875842 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.5565. Min Act: -0.1700
Data Index: 7477687 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.5565. Min Act: -0.1700
Data Index: 1761315 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.5253. Min Act: -0.1700
Data Index: 3079804 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.4940. Min Act: -0.1700
Data Index: 8156033 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.4940. Min Act: -0.1700
Data Index: 4868415 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.4940. Min Act: -0.1700
Data Index: 6071431 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.4628. Min Act: -0.1700
Data Index: 4702457 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.4628. Min Act: -0.1700
Data Index: 4497571 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5878. Min Range: -8.5878
Max Act: 7.4003. Min Act: -0.1700
Data Index: 3989105 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19