Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4818 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.3473. Min Act: -0.1700
Data Index: 4506678 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.3002. Min Act: -0.1700
Data Index: 1428580 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2531. Min Act: -0.1700
Data Index: 1694739 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2688. Min Act: -0.1700
Data Index: 3915525 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2531. Min Act: -0.1700
Data Index: 6675131 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2688. Min Act: -0.1700
Data Index: 2278685 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2531. Min Act: -0.1700
Data Index: 4339115 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2374. Min Act: -0.1700
Data Index: 5681773 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2374. Min Act: -0.1700
Data Index: 6122980 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2374. Min Act: -0.1700
Data Index: 7802657 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2216. Min Act: -0.1700
Data Index: 736468 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2216. Min Act: -0.1700
Data Index: 8682161 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2216. Min Act: -0.1700
Data Index: 8146025 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2216. Min Act: -0.1700
Data Index: 733372 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2059. Min Act: -0.1700
Data Index: 2392642 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2059. Min Act: -0.1700
Data Index: 4637860 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.2216. Min Act: -0.1700
Data Index: 7003967 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.1902. Min Act: -0.1700
Data Index: 3365363 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.1745. Min Act: -0.1700
Data Index: 372465 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3473. Min Range: -3.3473
Max Act: 3.1902. Min Act: -0.1700
Data Index: 4620162 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19