Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4489 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.2843. Min Range: -14.2843
Max Act: 14.2843. Min Act: -0.1700
Data Index: 132500 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.2843. Min Range: -14.2843
Max Act: 13.5968. Min Act: -0.1700
Data Index: 2510618 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.2843. Min Range: -14.2843
Max Act: 13.4093. Min Act: -0.1700
Data Index: 8447113 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.2843. Min Range: -14.2843
Max Act: 13.3468. Min Act: -0.1700
Data Index: 2156459 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.2843. Min Range: -14.2843
Max Act: 13.3468. Min Act: -0.1700
Data Index: 4027624 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.2843. Min Range: -14.2843
Max Act: 13.2218. Min Act: -0.1700
Data Index: 8734509 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.2843. Min Range: -14.2843
Max Act: 13.1593. Min Act: -0.1700
Data Index: 4101530 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.2843. Min Range: -14.2843
Max Act: 13.0968. Min Act: -0.1700
Data Index: 402862 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.9093. Min Act: -0.1700
Data Index: 1278138 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.8468. Min Act: -0.1700
Data Index: 898513 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.7218. Min Act: -0.1700
Data Index: 5365433 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.7843. Min Act: -0.1700
Data Index: 8238271 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.7218. Min Act: -0.1700
Data Index: 4550026 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.5968. Min Act: -0.1700
Data Index: 4893370 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.5968. Min Act: -0.1700
Data Index: 8225353 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.5968. Min Act: -0.1700
Data Index: 1484590 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.5343. Min Act: -0.1700
Data Index: 8087044 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.5343. Min Act: -0.1700
Data Index: 6612684 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.4718. Min Act: -0.1700
Data Index: 7890891 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.2843. Min Range: -14.2843
Max Act: 12.4718. Min Act: -0.1700
Data Index: 6704819 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19