Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2469 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.6470. Min Act: -0.1700
Data Index: 2242099 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.4907. Min Act: -0.1700
Data Index: 7287320 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.3970. Min Act: -0.1700
Data Index: 99515 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.3970. Min Act: -0.1700
Data Index: 4044717 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.3657. Min Act: -0.1700
Data Index: 4286389 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.2095. Min Act: -0.1700
Data Index: 5478506 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.1157. Min Act: -0.1700
Data Index: 2429382 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.1470. Min Act: -0.1700
Data Index: 2467717 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.0845. Min Act: -0.1700
Data Index: 557227 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.0845. Min Act: -0.1700
Data Index: 1280285 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.0845. Min Act: -0.1700
Data Index: 1489536 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.0845. Min Act: -0.1700
Data Index: 3629146 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.0532. Min Act: -0.1700
Data Index: 4559880 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.0220. Min Act: -0.1700
Data Index: 1636633 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.0220. Min Act: -0.1700
Data Index: 8828965 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.0220. Min Act: -0.1700
Data Index: 4049683 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6470. Min Range: -6.6470
Max Act: 5.9907. Min Act: -0.1700
Data Index: 874124 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6470. Min Range: -6.6470
Max Act: 5.9907. Min Act: -0.1700
Data Index: 2402230 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6470. Min Range: -6.6470
Max Act: 5.9907. Min Act: -0.1700
Data Index: 1149208 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6470. Min Range: -6.6470
Max Act: 5.9907. Min Act: -0.1700
Data Index: 126745 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19