Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2349. Min Range: -8.2349
Max Act: 8.2349. Min Act: -0.1700
Data Index: 8052335 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2349. Min Range: -8.2349
Max Act: 8.1099. Min Act: -0.1700
Data Index: 4902275 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2349. Min Range: -8.2349
Max Act: 8.1724. Min Act: -0.1700
Data Index: 7528349 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2349. Min Range: -8.2349
Max Act: 8.0474. Min Act: -0.1700
Data Index: 3853242 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2349. Min Range: -8.2349
Max Act: 8.0474. Min Act: -0.1700
Data Index: 813825 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2349. Min Range: -8.2349
Max Act: 8.0474. Min Act: -0.1700
Data Index: 5893548 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2349. Min Range: -8.2349
Max Act: 8.0474. Min Act: -0.1700
Data Index: 5890158 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2349. Min Range: -8.2349
Max Act: 8.0474. Min Act: -0.1700
Data Index: 657472 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2349. Min Range: -8.2349
Max Act: 8.0474. Min Act: -0.1700
Data Index: 1654834 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2349. Min Range: -8.2349
Max Act: 8.0474. Min Act: -0.1700
Data Index: 1654833 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2349. Min Range: -8.2349
Max Act: 7.9224. Min Act: -0.1700
Data Index: 1069749 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2349. Min Range: -8.2349
Max Act: 7.9224. Min Act: -0.1700
Data Index: 6307680 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2349. Min Range: -8.2349
Max Act: 7.9224. Min Act: -0.1700
Data Index: 8771366 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2349. Min Range: -8.2349
Max Act: 7.9224. Min Act: -0.1700
Data Index: 8271364 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2349. Min Range: -8.2349
Max Act: 7.9224. Min Act: -0.1700
Data Index: 7558168 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2349. Min Range: -8.2349
Max Act: 7.9224. Min Act: -0.1700
Data Index: 4133364 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2349. Min Range: -8.2349
Max Act: 7.9224. Min Act: -0.1700
Data Index: 5559655 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2349. Min Range: -8.2349
Max Act: 7.9224. Min Act: -0.1700
Data Index: 7104685 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2349. Min Range: -8.2349
Max Act: 7.9224. Min Act: -0.1700
Data Index: 5054565 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2349. Min Range: -8.2349
Max Act: 7.8599. Min Act: -0.1700
Data Index: 6401729 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19