Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2429 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2808. Min Range: -7.2808
Max Act: 7.2808. Min Act: -0.1700
Data Index: 4829600 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.9995. Min Act: -0.1700
Data Index: 5090576 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.8433. Min Act: -0.1700
Data Index: 628952 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.8433. Min Act: -0.1700
Data Index: 5090582 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.6558. Min Act: -0.1700
Data Index: 7068413 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.6245. Min Act: -0.1700
Data Index: 472863 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.5620. Min Act: -0.1700
Data Index: 472884 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.4683. Min Act: -0.1700
Data Index: 196892 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.3745. Min Act: -0.1700
Data Index: 6152586 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.4058. Min Act: -0.1700
Data Index: 7627452 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.3745. Min Act: -0.1700
Data Index: 6079827 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.3433. Min Act: -0.1700
Data Index: 8054494 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.2495. Min Act: -0.1700
Data Index: 6139288 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.2495. Min Act: -0.1700
Data Index: 2538229 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.3120. Min Act: -0.1700
Data Index: 4710553 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.2183. Min Act: -0.1700
Data Index: 3077238 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.2495. Min Act: -0.1700
Data Index: 3077239 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.2495. Min Act: -0.1700
Data Index: 5361398 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.2495. Min Act: -0.1700
Data Index: 6033174 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2808. Min Range: -7.2808
Max Act: 6.1870. Min Act: -0.1700
Data Index: 3195872 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19