Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2707 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2221. Min Range: -8.2221
Max Act: 8.2221. Min Act: -0.1700
Data Index: 886390 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2221. Min Range: -8.2221
Max Act: 8.0971. Min Act: -0.1700
Data Index: 4595585 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2221. Min Range: -8.2221
Max Act: 8.0971. Min Act: -0.1700
Data Index: 8737412 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2221. Min Range: -8.2221
Max Act: 8.0346. Min Act: -0.1700
Data Index: 4662560 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2221. Min Range: -8.2221
Max Act: 8.0346. Min Act: -0.1700
Data Index: 4599258 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2221. Min Range: -8.2221
Max Act: 8.0346. Min Act: -0.1700
Data Index: 7920283 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2221. Min Range: -8.2221
Max Act: 8.0346. Min Act: -0.1700
Data Index: 3901303 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.9721. Min Act: -0.1700
Data Index: 6264978 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.9721. Min Act: -0.1700
Data Index: 7003292 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.9096. Min Act: -0.1700
Data Index: 5043203 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.9096. Min Act: -0.1700
Data Index: 5537766 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.9096. Min Act: -0.1700
Data Index: 3690729 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.7846. Min Act: -0.1700
Data Index: 2025892 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.8471. Min Act: -0.1700
Data Index: 5311816 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.8471. Min Act: -0.1700
Data Index: 7171567 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.8471. Min Act: -0.1700
Data Index: 3447116 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.8471. Min Act: -0.1700
Data Index: 3911810 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.7846. Min Act: -0.1700
Data Index: 6418106 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.7846. Min Act: -0.1700
Data Index: 2555364 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2221. Min Range: -8.2221
Max Act: 7.7846. Min Act: -0.1700
Data Index: 464666 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19