Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.2740. Min Act: -0.1700
Data Index: 3571032 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.2115. Min Act: -0.1700
Data Index: 3953942 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.1802. Min Act: -0.1700
Data Index: 2779082 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.1802. Min Act: -0.1700
Data Index: 7131680 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.1802. Min Act: -0.1700
Data Index: 3879430 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.1177. Min Act: -0.1700
Data Index: 4894520 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.1177. Min Act: -0.1700
Data Index: 3571031 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.0865. Min Act: -0.1700
Data Index: 7656935 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.0865. Min Act: -0.1700
Data Index: 413120 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.0552. Min Act: -0.1700
Data Index: 6311603 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.0240. Min Act: -0.1700
Data Index: 7645695 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.0240. Min Act: -0.1700
Data Index: 630100 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.0552. Min Act: -0.1700
Data Index: 7821809 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2740. Min Range: -6.2740
Max Act: 5.9927. Min Act: -0.1700
Data Index: 8443404 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2740. Min Range: -6.2740
Max Act: 5.9927. Min Act: -0.1700
Data Index: 8002787 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2740. Min Range: -6.2740
Max Act: 5.9927. Min Act: -0.1700
Data Index: 1676363 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2740. Min Range: -6.2740
Max Act: 5.9927. Min Act: -0.1700
Data Index: 2226337 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2740. Min Range: -6.2740
Max Act: 5.9615. Min Act: -0.1700
Data Index: 735244 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2740. Min Range: -6.2740
Max Act: 5.9927. Min Act: -0.1700
Data Index: 3435728 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2740. Min Range: -6.2740
Max Act: 5.9615. Min Act: -0.1700
Data Index: 4185923 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19