Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2959 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.7303. Min Act: -0.1700
Data Index: 7506111 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.6053. Min Act: -0.1700
Data Index: 6119165 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.4491. Min Act: -0.1700
Data Index: 3893244 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.3241. Min Act: -0.1700
Data Index: 7389594 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.2928. Min Act: -0.1700
Data Index: 7349094 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.2928. Min Act: -0.1700
Data Index: 1403042 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.1678. Min Act: -0.1700
Data Index: 7251202 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.1366. Min Act: -0.1700
Data Index: 8187560 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.1366. Min Act: -0.1700
Data Index: 1573215 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.1366. Min Act: -0.1700
Data Index: 330873 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.1678. Min Act: -0.1700
Data Index: 7598819 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.1053. Min Act: -0.1700
Data Index: 1616920 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.0741. Min Act: -0.1700
Data Index: 847776 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.0428. Min Act: -0.1700
Data Index: 8777523 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.0741. Min Act: -0.1700
Data Index: 5635339 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.0741. Min Act: -0.1700
Data Index: 3558419 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.0428. Min Act: -0.1700
Data Index: 2032322 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.0116. Min Act: -0.1700
Data Index: 754421 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7303. Min Range: -7.7303
Max Act: 7.0116. Min Act: -0.1700
Data Index: 7182576 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7303. Min Range: -7.7303
Max Act: 6.9803. Min Act: -0.1700
Data Index: 4598818 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19