Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.4757. Min Act: -0.1700
Data Index: 4287926 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.1944. Min Act: -0.1700
Data Index: 8442867 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.1944. Min Act: -0.1700
Data Index: 2140370 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.1632. Min Act: -0.1700
Data Index: 4429103 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.1632. Min Act: -0.1700
Data Index: 6796737 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.1319. Min Act: -0.1700
Data Index: 4315739 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.1319. Min Act: -0.1700
Data Index: 393350 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.1007. Min Act: -0.1700
Data Index: 6362428 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.1319. Min Act: -0.1700
Data Index: 7425386 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.1007. Min Act: -0.1700
Data Index: 5179910 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.1007. Min Act: -0.1700
Data Index: 4758759 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.1007. Min Act: -0.1700
Data Index: 3368935 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.0694. Min Act: -0.1700
Data Index: 1712339 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.0694. Min Act: -0.1700
Data Index: 8224561 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.0694. Min Act: -0.1700
Data Index: 1419409 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.0694. Min Act: -0.1700
Data Index: 3320536 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.0382. Min Act: -0.1700
Data Index: 4136714 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.0382. Min Act: -0.1700
Data Index: 6029897 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.0382. Min Act: -0.1700
Data Index: 3593077 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4757. Min Range: -5.4757
Max Act: 5.0382. Min Act: -0.1700
Data Index: 7369502 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19