Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1906 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.2906. Min Act: -0.1700
Data Index: 4044465 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.2593. Min Act: -0.1700
Data Index: 2623764 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.1656. Min Act: -0.1700
Data Index: 121340 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.1656. Min Act: -0.1700
Data Index: 6227046 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.1343. Min Act: -0.1700
Data Index: 176161 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.1031. Min Act: -0.1700
Data Index: 7249910 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.1031. Min Act: -0.1700
Data Index: 86362 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.1031. Min Act: -0.1700
Data Index: 3093332 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.0718. Min Act: -0.1700
Data Index: 8551675 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.0718. Min Act: -0.1700
Data Index: 4128278 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.0718. Min Act: -0.1700
Data Index: 8447966 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.0406. Min Act: -0.1700
Data Index: 5081193 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.0406. Min Act: -0.1700
Data Index: 1140004 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.0093. Min Act: -0.1700
Data Index: 4476780 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.0093. Min Act: -0.1700
Data Index: 4315649 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.0093. Min Act: -0.1700
Data Index: 4621950 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2906. Min Range: -6.2906
Max Act: 6.0093. Min Act: -0.1700
Data Index: 702732 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2906. Min Range: -6.2906
Max Act: 5.9781. Min Act: -0.1700
Data Index: 5121448 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2906. Min Range: -6.2906
Max Act: 5.9781. Min Act: -0.1700
Data Index: 813051 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2906. Min Range: -6.2906
Max Act: 5.9468. Min Act: -0.1700
Data Index: 3716011 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19