Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.9631. Min Act: -0.1700
Data Index: 2504518 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.8381. Min Act: -0.1700
Data Index: 3555359 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.8381. Min Act: -0.1700
Data Index: 1119471 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.7756. Min Act: -0.1700
Data Index: 7390038 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.7756. Min Act: -0.1700
Data Index: 8739584 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.7756. Min Act: -0.1700
Data Index: 1485620 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.7756. Min Act: -0.1700
Data Index: 5337997 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.7756. Min Act: -0.1700
Data Index: 3395431 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.7443. Min Act: -0.1700
Data Index: 1778306 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.7443. Min Act: -0.1700
Data Index: 7894165 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.7131. Min Act: -0.1700
Data Index: 3723833 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.6818. Min Act: -0.1700
Data Index: 7803957 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.6818. Min Act: -0.1700
Data Index: 4433630 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.6818. Min Act: -0.1700
Data Index: 5939642 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.6506. Min Act: -0.1700
Data Index: 1191386 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.6506. Min Act: -0.1700
Data Index: 8393865 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.6506. Min Act: -0.1700
Data Index: 6962306 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.6193. Min Act: -0.1700
Data Index: 711466 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.6193. Min Act: -0.1700
Data Index: 2951631 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9631. Min Range: -4.9631
Max Act: 4.6193. Min Act: -0.1700
Data Index: 3884810 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19