Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.9673. Min Act: -0.1700
Data Index: 4905636 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.8736. Min Act: -0.1700
Data Index: 4908766 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.7486. Min Act: -0.1700
Data Index: 7914394 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.4673. Min Act: -0.1700
Data Index: 2147548 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.4361. Min Act: -0.1700
Data Index: 2108216 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.4361. Min Act: -0.1700
Data Index: 5453379 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.3736. Min Act: -0.1700
Data Index: 3114676 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.3423. Min Act: -0.1700
Data Index: 2114704 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.3423. Min Act: -0.1700
Data Index: 966178 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.3423. Min Act: -0.1700
Data Index: 7345067 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.3423. Min Act: -0.1700
Data Index: 5168226 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.2798. Min Act: -0.1700
Data Index: 3606995 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.2798. Min Act: -0.1700
Data Index: 3055851 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.2798. Min Act: -0.1700
Data Index: 363326 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.2798. Min Act: -0.1700
Data Index: 8551120 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.2798. Min Act: -0.1700
Data Index: 8400536 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.2486. Min Act: -0.1700
Data Index: 3634164 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.2486. Min Act: -0.1700
Data Index: 4787585 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.2486. Min Act: -0.1700
Data Index: 1660513 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9673. Min Range: -4.9673
Max Act: 4.2486. Min Act: -0.1700
Data Index: 6966887 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19