Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 476 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.8787. Min Act: -0.1700
Data Index: 5120899 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.5037. Min Act: -0.1700
Data Index: 8546187 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.5037. Min Act: -0.1700
Data Index: 4501849 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.4100. Min Act: -0.1700
Data Index: 1420349 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.4412. Min Act: -0.1700
Data Index: 3055170 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.4412. Min Act: -0.1700
Data Index: 8291805 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.3787. Min Act: -0.1700
Data Index: 8808035 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.3475. Min Act: -0.1700
Data Index: 6067758 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.3162. Min Act: -0.1700
Data Index: 8437950 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.3162. Min Act: -0.1700
Data Index: 1924209 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.3162. Min Act: -0.1700
Data Index: 7942054 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.2537. Min Act: -0.1700
Data Index: 7489313 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.2850. Min Act: -0.1700
Data Index: 4294441 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.2850. Min Act: -0.1700
Data Index: 4188861 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.2537. Min Act: -0.1700
Data Index: 6073489 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.2537. Min Act: -0.1700
Data Index: 4941641 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.2537. Min Act: -0.1700
Data Index: 2723402 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.2537. Min Act: -0.1700
Data Index: 3934030 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.2537. Min Act: -0.1700
Data Index: 7315127 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8787. Min Range: -6.8787
Max Act: 6.1912. Min Act: -0.1700
Data Index: 5076769 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19