Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 461 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1037. Min Range: -3.1037
Max Act: 3.1037. Min Act: -0.1700
Data Index: 1323054 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1037. Min Range: -3.1037
Max Act: 3.1037. Min Act: -0.1700
Data Index: 3594214 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1037. Min Range: -3.1037
Max Act: 3.0407. Min Act: -0.1700
Data Index: 3419236 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1037. Min Range: -3.1037
Max Act: 3.0249. Min Act: -0.1700
Data Index: 2822462 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1037. Min Range: -3.1037
Max Act: 3.0091. Min Act: -0.1700
Data Index: 1039628 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1037. Min Range: -3.1037
Max Act: 3.0249. Min Act: -0.1700
Data Index: 2989314 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1037. Min Range: -3.1037
Max Act: 3.0091. Min Act: -0.1700
Data Index: 2151975 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1037. Min Range: -3.1037
Max Act: 3.0091. Min Act: -0.1700
Data Index: 1709921 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9774. Min Act: -0.1700
Data Index: 2077738 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9774. Min Act: -0.1700
Data Index: 4876379 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9774. Min Act: -0.1700
Data Index: 788323 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9933. Min Act: -0.1700
Data Index: 316397 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9774. Min Act: -0.1700
Data Index: 1242945 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9774. Min Act: -0.1700
Data Index: 6338031 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9616. Min Act: -0.1700
Data Index: 2984698 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9774. Min Act: -0.1700
Data Index: 7755219 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9616. Min Act: -0.1700
Data Index: 5822545 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9300. Min Act: -0.1700
Data Index: 473123 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9616. Min Act: -0.1700
Data Index: 2339789 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1037. Min Range: -3.1037
Max Act: 2.9616. Min Act: -0.1700
Data Index: 6689884 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19