Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4672 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.2877. Min Act: -0.1700
Data Index: 1723188 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.2249. Min Act: -0.1700
Data Index: 1778666 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.2092. Min Act: -0.1700
Data Index: 4940040 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.1934. Min Act: -0.1700
Data Index: 2890037 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.1934. Min Act: -0.1700
Data Index: 7795351 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.1620. Min Act: -0.1700
Data Index: 4468917 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.1620. Min Act: -0.1700
Data Index: 3760624 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.1462. Min Act: -0.1700
Data Index: 513575 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.0990. Min Act: -0.1700
Data Index: 4445665 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.1147. Min Act: -0.1700
Data Index: 5878609 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.1147. Min Act: -0.1700
Data Index: 3040063 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.0990. Min Act: -0.1700
Data Index: 233819 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.0990. Min Act: -0.1700
Data Index: 3800986 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.0832. Min Act: -0.1700
Data Index: 1906224 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.0674. Min Act: -0.1700
Data Index: 6416218 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.0990. Min Act: -0.1700
Data Index: 8120091 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.0674. Min Act: -0.1700
Data Index: 435642 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.0674. Min Act: -0.1700
Data Index: 516100 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.0517. Min Act: -0.1700
Data Index: 5486767 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2877. Min Range: -3.2877
Max Act: 3.0674. Min Act: -0.1700
Data Index: 3043090 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19