Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.2406. Min Act: -0.1700
Data Index: 4645547 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0843. Min Act: -0.1700
Data Index: 1009634 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.9593. Min Act: -0.1700
Data Index: 399944 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.9906. Min Act: -0.1700
Data Index: 1814015 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.9593. Min Act: -0.1700
Data Index: 8739762 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.8968. Min Act: -0.1700
Data Index: 4319725 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.8968. Min Act: -0.1700
Data Index: 5393251 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.8343. Min Act: -0.1700
Data Index: 1700240 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.8343. Min Act: -0.1700
Data Index: 2461567 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.8343. Min Act: -0.1700
Data Index: 188176 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.8031. Min Act: -0.1700
Data Index: 3473922 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.8031. Min Act: -0.1700
Data Index: 6865692 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.7718. Min Act: -0.1700
Data Index: 4947900 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.7718. Min Act: -0.1700
Data Index: 6300562 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.7406. Min Act: -0.1700
Data Index: 4662322 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.7093. Min Act: -0.1700
Data Index: 607168 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.7093. Min Act: -0.1700
Data Index: 8163226 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.6781. Min Act: -0.1700
Data Index: 8571797 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.7093. Min Act: -0.1700
Data Index: 4670766 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2406. Min Range: -5.2406
Max Act: 4.7093. Min Act: -0.1700
Data Index: 2119613 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19