Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 458 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.7750. Min Act: -0.1700
Data Index: 4221280 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.7750. Min Act: -0.1700
Data Index: 3302372 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.6812. Min Act: -0.1700
Data Index: 7562012 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.6500. Min Act: -0.1700
Data Index: 203392 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.6500. Min Act: -0.1700
Data Index: 574797 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.6187. Min Act: -0.1700
Data Index: 2072213 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.6187. Min Act: -0.1700
Data Index: 2743121 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.5875. Min Act: -0.1700
Data Index: 5096382 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.5875. Min Act: -0.1700
Data Index: 2450736 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.5875. Min Act: -0.1700
Data Index: 2252143 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.5562. Min Act: -0.1700
Data Index: 791375 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.5250. Min Act: -0.1700
Data Index: 8501521 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.5250. Min Act: -0.1700
Data Index: 5634956 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.5562. Min Act: -0.1700
Data Index: 1271563 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.5250. Min Act: -0.1700
Data Index: 6520341 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.4937. Min Act: -0.1700
Data Index: 1374102 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.4937. Min Act: -0.1700
Data Index: 1478396 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.4937. Min Act: -0.1700
Data Index: 6977639 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.4937. Min Act: -0.1700
Data Index: 2771543 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7750. Min Range: -4.7750
Max Act: 4.4625. Min Act: -0.1700
Data Index: 3488719 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19