Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.9102. Min Act: -0.1700
Data Index: 1565368 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.7540. Min Act: -0.1700
Data Index: 7808433 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.5977. Min Act: -0.1700
Data Index: 7727875 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.5040. Min Act: -0.1700
Data Index: 1892050 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.4415. Min Act: -0.1700
Data Index: 4840591 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.4415. Min Act: -0.1700
Data Index: 699372 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.4102. Min Act: -0.1700
Data Index: 6880204 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.4415. Min Act: -0.1700
Data Index: 7982970 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.4102. Min Act: -0.1700
Data Index: 3639133 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.3790. Min Act: -0.1700
Data Index: 422491 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.3477. Min Act: -0.1700
Data Index: 6710759 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2540. Min Act: -0.1700
Data Index: 4694489 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2540. Min Act: -0.1700
Data Index: 7651489 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2227. Min Act: -0.1700
Data Index: 8652886 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2227. Min Act: -0.1700
Data Index: 4488614 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2227. Min Act: -0.1700
Data Index: 52328 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2227. Min Act: -0.1700
Data Index: 4715450 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2227. Min Act: -0.1700
Data Index: 7306996 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2227. Min Act: -0.1700
Data Index: 2432411 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2227. Min Act: -0.1700
Data Index: 145598 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19