Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.6565. Min Act: -0.1700
Data Index: 4996588 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.5940. Min Act: -0.1700
Data Index: 8560980 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.5315. Min Act: -0.1700
Data Index: 4315496 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.4377. Min Act: -0.1700
Data Index: 220600 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.4065. Min Act: -0.1700
Data Index: 6272142 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.4065. Min Act: -0.1700
Data Index: 4260265 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.3440. Min Act: -0.1700
Data Index: 4341773 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.3127. Min Act: -0.1700
Data Index: 3479363 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.3127. Min Act: -0.1700
Data Index: 5584344 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.3127. Min Act: -0.1700
Data Index: 5859410 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.3440. Min Act: -0.1700
Data Index: 1760828 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.2815. Min Act: -0.1700
Data Index: 661645 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.2815. Min Act: -0.1700
Data Index: 1832877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.2502. Min Act: -0.1700
Data Index: 1516489 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.2502. Min Act: -0.1700
Data Index: 1703917 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.1877. Min Act: -0.1700
Data Index: 1234046 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.1565. Min Act: -0.1700
Data Index: 2765671 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.1565. Min Act: -0.1700
Data Index: 4620288 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.1877. Min Act: -0.1700
Data Index: 3297574 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6565. Min Range: -6.6565
Max Act: 6.1565. Min Act: -0.1700
Data Index: 7361752 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19