Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1672 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.3529. Min Act: -0.1700
Data Index: 5404827 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.2591. Min Act: -0.1700
Data Index: 8560232 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1966. Min Act: -0.1700
Data Index: 4295642 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.2279. Min Act: -0.1700
Data Index: 5352495 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1966. Min Act: -0.1700
Data Index: 8276092 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1654. Min Act: -0.1700
Data Index: 3451530 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1654. Min Act: -0.1700
Data Index: 8560236 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1341. Min Act: -0.1700
Data Index: 5273015 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1341. Min Act: -0.1700
Data Index: 921601 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1029. Min Act: -0.1700
Data Index: 1366478 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1029. Min Act: -0.1700
Data Index: 8560235 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1029. Min Act: -0.1700
Data Index: 5614916 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1029. Min Act: -0.1700
Data Index: 7526964 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1029. Min Act: -0.1700
Data Index: 8276093 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.0404. Min Act: -0.1700
Data Index: 3367679 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.0716. Min Act: -0.1700
Data Index: 1868820 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.0716. Min Act: -0.1700
Data Index: 202861 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.0716. Min Act: -0.1700
Data Index: 6468090 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.0716. Min Act: -0.1700
Data Index: 3518035 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.0716. Min Act: -0.1700
Data Index: 833996 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19