Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 495 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4488. Min Range: -8.4488
Max Act: 8.4488. Min Act: -0.1700
Data Index: 4269872 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4488. Min Range: -8.4488
Max Act: 8.0738. Min Act: -0.1700
Data Index: 1208329 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4488. Min Range: -8.4488
Max Act: 8.0113. Min Act: -0.1700
Data Index: 2852919 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4488. Min Range: -8.4488
Max Act: 8.0113. Min Act: -0.1700
Data Index: 6142378 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.9488. Min Act: -0.1700
Data Index: 2800447 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.8863. Min Act: -0.1700
Data Index: 8428546 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.8238. Min Act: -0.1700
Data Index: 85359 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.7613. Min Act: -0.1700
Data Index: 8433443 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.6363. Min Act: -0.1700
Data Index: 4673805 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.6988. Min Act: -0.1700
Data Index: 2088094 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.6988. Min Act: -0.1700
Data Index: 6670425 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.6363. Min Act: -0.1699
Data Index: 3757513 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.6363. Min Act: -0.1700
Data Index: 399982 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.6363. Min Act: -0.1700
Data Index: 998863 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.5738. Min Act: -0.1700
Data Index: 5126490 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.5738. Min Act: -0.1700
Data Index: 2088093 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.5738. Min Act: -0.1700
Data Index: 537406 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.5738. Min Act: -0.1700
Data Index: 2515476 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.5738. Min Act: -0.1700
Data Index: 3712668 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4488. Min Range: -8.4488
Max Act: 7.5738. Min Act: -0.1700
Data Index: 4651628 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19