Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5418 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.4548. Min Act: -0.1700
Data Index: 6055885 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.3298. Min Act: -0.1700
Data Index: 2253300 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.3610. Min Act: -0.1700
Data Index: 5814153 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.3298. Min Act: -0.1700
Data Index: 6515515 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.2985. Min Act: -0.1700
Data Index: 703370 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.2985. Min Act: -0.1700
Data Index: 8270138 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.2360. Min Act: -0.1700
Data Index: 4188702 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.2360. Min Act: -0.1700
Data Index: 8140977 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.2048. Min Act: -0.1700
Data Index: 6103817 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.2048. Min Act: -0.1700
Data Index: 5294041 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.2048. Min Act: -0.1700
Data Index: 1572981 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.2360. Min Act: -0.1700
Data Index: 5497851 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.1735. Min Act: -0.1700
Data Index: 8179932 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.1735. Min Act: -0.1700
Data Index: 7629013 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.1735. Min Act: -0.1700
Data Index: 3531907 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.1735. Min Act: -0.1700
Data Index: 3420296 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.1423. Min Act: -0.1700
Data Index: 271571 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.1423. Min Act: -0.1700
Data Index: 5155002 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.1110. Min Act: -0.1700
Data Index: 6210241 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.1110. Min Act: -0.1700
Data Index: 4471200 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19