Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6404. Min Range: -12.6404
Max Act: 12.6404. Min Act: -0.1700
Data Index: 2494290 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6404. Min Range: -12.6404
Max Act: 12.3279. Min Act: -0.1700
Data Index: 714197 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6404. Min Range: -12.6404
Max Act: 11.8904. Min Act: -0.1700
Data Index: 5716426 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6404. Min Range: -12.6404
Max Act: 11.5779. Min Act: -0.1700
Data Index: 2081584 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6404. Min Range: -12.6404
Max Act: 11.5154. Min Act: -0.1700
Data Index: 6465601 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6404. Min Range: -12.6404
Max Act: 11.4529. Min Act: -0.1700
Data Index: 6747433 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6404. Min Range: -12.6404
Max Act: 11.4529. Min Act: -0.1699
Data Index: 4451551 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6404. Min Range: -12.6404
Max Act: 11.3904. Min Act: -0.1699
Data Index: 5965462 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6404. Min Range: -12.6404
Max Act: 11.3279. Min Act: -0.1700
Data Index: 8479780 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6404. Min Range: -12.6404
Max Act: 11.1404. Min Act: -0.1700
Data Index: 5908544 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6404. Min Range: -12.6404
Max Act: 11.0154. Min Act: -0.1700
Data Index: 5468758 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6404. Min Range: -12.6404
Max Act: 11.0154. Min Act: -0.1700
Data Index: 6177147 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6404. Min Range: -12.6404
Max Act: 10.9529. Min Act: -0.1700
Data Index: 76225 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6404. Min Range: -12.6404
Max Act: 10.8279. Min Act: -0.1700
Data Index: 6148894 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6404. Min Range: -12.6404
Max Act: 10.7654. Min Act: -0.1698
Data Index: 496234 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6404. Min Range: -12.6404
Max Act: 10.3904. Min Act: -0.1700
Data Index: 1845790 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6404. Min Range: -12.6404
Max Act: 10.3904. Min Act: -0.1700
Data Index: 8583090 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6404. Min Range: -12.6404
Max Act: 10.3279. Min Act: -0.1700
Data Index: 2563363 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6404. Min Range: -12.6404
Max Act: 10.3279. Min Act: -0.1700
Data Index: 5572885 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6404. Min Range: -12.6404
Max Act: 10.2654. Min Act: -0.1699
Data Index: 1865610 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19