Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4892 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.7806. Min Act: -0.1700
Data Index: 8314929 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.7181. Min Act: -0.1700
Data Index: 8150610 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.6556. Min Act: -0.1700
Data Index: 4852166 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.5619. Min Act: -0.1700
Data Index: 3167301 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.5306. Min Act: -0.1700
Data Index: 6908079 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.4681. Min Act: -0.1700
Data Index: 4324508 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.4681. Min Act: -0.1700
Data Index: 3577469 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.4681. Min Act: -0.1700
Data Index: 3419140 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.4056. Min Act: -0.1700
Data Index: 7900530 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.4056. Min Act: -0.1700
Data Index: 1674582 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.3119. Min Act: -0.1700
Data Index: 2255958 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.2494. Min Act: -0.1700
Data Index: 4228569 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.2494. Min Act: -0.1700
Data Index: 4536926 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.2494. Min Act: -0.1700
Data Index: 1720220 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.2181. Min Act: -0.1700
Data Index: 384769 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.2181. Min Act: -0.1700
Data Index: 7595417 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.2181. Min Act: -0.1700
Data Index: 3796352 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.1869. Min Act: -0.1700
Data Index: 3219268 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.1556. Min Act: -0.1700
Data Index: 5048945 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7806. Min Range: -5.7806
Max Act: 5.1869. Min Act: -0.1700
Data Index: 4530929 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19