Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1679. Min Range: -7.1679
Max Act: 7.1679. Min Act: -0.1700
Data Index: 8322005 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1679. Min Range: -7.1679
Max Act: 7.0116. Min Act: -0.1700
Data Index: 3339739 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.6054. Min Act: -0.1700
Data Index: 3048938 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.6054. Min Act: -0.1700
Data Index: 8519330 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.5741. Min Act: -0.1700
Data Index: 1469547 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.5429. Min Act: -0.1700
Data Index: 8138363 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.5116. Min Act: -0.1700
Data Index: 4911441 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.4804. Min Act: -0.1700
Data Index: 3914361 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.4491. Min Act: -0.1700
Data Index: 2384477 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.3866. Min Act: -0.1700
Data Index: 4373154 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.3554. Min Act: -0.1700
Data Index: 7821975 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.3554. Min Act: -0.1700
Data Index: 4671356 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.3866. Min Act: -0.1700
Data Index: 596177 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.2929. Min Act: -0.1700
Data Index: 5076725 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.2929. Min Act: -0.1700
Data Index: 7986137 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.2616. Min Act: -0.1700
Data Index: 866384 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.2616. Min Act: -0.1700
Data Index: 879569 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.2616. Min Act: -0.1700
Data Index: 8201494 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.2304. Min Act: -0.1700
Data Index: 3542683 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1679. Min Range: -7.1679
Max Act: 6.1991. Min Act: -0.1700
Data Index: 4900137 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19