Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3339 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2485. Min Range: -5.2485
Max Act: 5.2485. Min Act: -0.1700
Data Index: 3990610 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2485. Min Range: -5.2485
Max Act: 5.0923. Min Act: -0.1700
Data Index: 4364303 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2485. Min Range: -5.2485
Max Act: 5.0610. Min Act: -0.1700
Data Index: 6796977 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.9360. Min Act: -0.1700
Data Index: 3189980 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.9673. Min Act: -0.1700
Data Index: 5948367 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.9360. Min Act: -0.1700
Data Index: 8773688 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.9048. Min Act: -0.1700
Data Index: 6903006 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.8110. Min Act: -0.1700
Data Index: 4570985 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.7485. Min Act: -0.1700
Data Index: 7691146 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.7485. Min Act: -0.1700
Data Index: 4125636 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.7173. Min Act: -0.1700
Data Index: 4899481 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.6860. Min Act: -0.1700
Data Index: 4891179 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.6860. Min Act: -0.1700
Data Index: 2862792 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.6548. Min Act: -0.1700
Data Index: 5251574 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.6548. Min Act: -0.1700
Data Index: 7596056 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.6548. Min Act: -0.1700
Data Index: 3305685 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.6235. Min Act: -0.1700
Data Index: 2360132 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.6235. Min Act: -0.1700
Data Index: 4483001 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.6235. Min Act: -0.1700
Data Index: 2572003 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2485. Min Range: -5.2485
Max Act: 4.6235. Min Act: -0.1700
Data Index: 8438300 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19