Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6012 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1019. Min Range: -6.1019
Max Act: 6.1019. Min Act: -0.1700
Data Index: 4902674 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1019. Min Range: -6.1019
Max Act: 6.0394. Min Act: -0.1700
Data Index: 8000004 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1019. Min Range: -6.1019
Max Act: 6.0081. Min Act: -0.1700
Data Index: 8660210 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.9456. Min Act: -0.1700
Data Index: 3411215 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.9456. Min Act: -0.1700
Data Index: 3769850 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.8831. Min Act: -0.1700
Data Index: 6036937 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.8831. Min Act: -0.1700
Data Index: 4963849 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.8206. Min Act: -0.1700
Data Index: 6068153 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.8206. Min Act: -0.1700
Data Index: 6822714 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.8206. Min Act: -0.1700
Data Index: 4272706 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.8206. Min Act: -0.1700
Data Index: 6966600 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.7894. Min Act: -0.1700
Data Index: 1308881 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.7894. Min Act: -0.1700
Data Index: 6425344 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.7894. Min Act: -0.1700
Data Index: 4780478 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.7894. Min Act: -0.1700
Data Index: 3006469 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.7269. Min Act: -0.1700
Data Index: 8683268 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.7269. Min Act: -0.1700
Data Index: 3812637 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.7269. Min Act: -0.1700
Data Index: 1499961 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.7269. Min Act: -0.1700
Data Index: 2023574 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1019. Min Range: -6.1019
Max Act: 5.7269. Min Act: -0.1700
Data Index: 8136332 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19