Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0565. Min Range: -7.0565
Max Act: 7.0565. Min Act: -0.1700
Data Index: 1097459 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.9315. Min Act: -0.1700
Data Index: 2235182 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.9315. Min Act: -0.1700
Data Index: 7858371 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.8690. Min Act: -0.1700
Data Index: 8810748 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.8378. Min Act: -0.1700
Data Index: 4751250 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.7753. Min Act: -0.1700
Data Index: 5651970 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.6815. Min Act: -0.1700
Data Index: 5034319 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.7128. Min Act: -0.1700
Data Index: 56480 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.6503. Min Act: -0.1700
Data Index: 4437631 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.6503. Min Act: -0.1700
Data Index: 6702407 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.6190. Min Act: -0.1700
Data Index: 7518268 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.6190. Min Act: -0.1700
Data Index: 3492208 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.5878. Min Act: -0.1700
Data Index: 6451418 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.5253. Min Act: -0.1700
Data Index: 6102118 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.5565. Min Act: -0.1700
Data Index: 7016681 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.4940. Min Act: -0.1700
Data Index: 3038391 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.5565. Min Act: -0.1700
Data Index: 1218255 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.4628. Min Act: -0.1700
Data Index: 8223091 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.4628. Min Act: -0.1700
Data Index: 7314751 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0565. Min Range: -7.0565
Max Act: 6.4940. Min Act: -0.1700
Data Index: 3177667 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19