Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.2722. Min Act: -0.1700
Data Index: 2862812 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.2060. Min Act: -0.1700
Data Index: 6334309 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.1894. Min Act: -0.1700
Data Index: 1832749 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.1562. Min Act: -0.1700
Data Index: 8017380 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.1395. Min Act: -0.1700
Data Index: 1167777 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.1061. Min Act: -0.1700
Data Index: 2332969 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.1061. Min Act: -0.1700
Data Index: 825562 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0726. Min Act: -0.1700
Data Index: 749240 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0893. Min Act: -0.1700
Data Index: 5698251 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0893. Min Act: -0.1700
Data Index: 3020799 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0893. Min Act: -0.1700
Data Index: 8769052 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0726. Min Act: -0.1700
Data Index: 4260632 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.1061. Min Act: -0.1700
Data Index: 5779645 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0726. Min Act: -0.1700
Data Index: 6580252 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0726. Min Act: -0.1700
Data Index: 472587 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0726. Min Act: -0.1700
Data Index: 482067 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0893. Min Act: -0.1700
Data Index: 8548861 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0389. Min Act: -0.1700
Data Index: 4658010 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0558. Min Act: -0.1700
Data Index: 1698282 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2722. Min Range: -2.2722
Max Act: 2.0389. Min Act: -0.1700
Data Index: 2808210 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19