Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1823 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.9440. Min Act: -0.1700
Data Index: 8252487 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.7878. Min Act: -0.1700
Data Index: 5958087 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.7565. Min Act: -0.1700
Data Index: 4519996 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.6940. Min Act: -0.1700
Data Index: 3771988 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.6940. Min Act: -0.1700
Data Index: 6667547 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.6628. Min Act: -0.1700
Data Index: 4400901 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.6315. Min Act: -0.1700
Data Index: 3465477 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.6628. Min Act: -0.1700
Data Index: 2816531 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.6315. Min Act: -0.1700
Data Index: 4029935 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.6315. Min Act: -0.1700
Data Index: 5870152 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.5690. Min Act: -0.1700
Data Index: 3465479 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.6003. Min Act: -0.1700
Data Index: 3367514 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.6003. Min Act: -0.1700
Data Index: 2741605 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.5690. Min Act: -0.1700
Data Index: 7578751 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.6003. Min Act: -0.1700
Data Index: 3165585 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.6003. Min Act: -0.1700
Data Index: 3465476 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.5378. Min Act: -0.1700
Data Index: 4164169 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.5690. Min Act: -0.1700
Data Index: 2870788 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.5690. Min Act: -0.1700
Data Index: 1717960 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9440. Min Range: -5.9440
Max Act: 5.5378. Min Act: -0.1700
Data Index: 2291088 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19