Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.6011. Min Act: -0.1700
Data Index: 3072400 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.5699. Min Act: -0.1700
Data Index: 3586931 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.5074. Min Act: -0.1700
Data Index: 6912910 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.5074. Min Act: -0.1700
Data Index: 1914204 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.4449. Min Act: -0.1700
Data Index: 1992396 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.3824. Min Act: -0.1700
Data Index: 7072135 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.3824. Min Act: -0.1700
Data Index: 1992919 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.3511. Min Act: -0.1700
Data Index: 1414879 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.3511. Min Act: -0.1700
Data Index: 5729765 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.2886. Min Act: -0.1700
Data Index: 3460457 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.3199. Min Act: -0.1700
Data Index: 4506835 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.2574. Min Act: -0.1700
Data Index: 1876701 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.2886. Min Act: -0.1700
Data Index: 5005510 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.2574. Min Act: -0.1700
Data Index: 2003783 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.2574. Min Act: -0.1700
Data Index: 664502 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.2574. Min Act: -0.1700
Data Index: 2884129 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.2886. Min Act: -0.1700
Data Index: 1690274 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.2574. Min Act: -0.1700
Data Index: 2444771 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.2886. Min Act: -0.1700
Data Index: 442170 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6011. Min Range: -6.6011
Max Act: 6.2261. Min Act: -0.1700
Data Index: 8576317 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19