Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1912 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.6662. Min Act: -0.1700
Data Index: 2168297 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.3850. Min Act: -0.1700
Data Index: 2044013 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.3225. Min Act: -0.1700
Data Index: 6033576 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.3225. Min Act: -0.1700
Data Index: 6607488 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.2600. Min Act: -0.1700
Data Index: 4850601 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.2600. Min Act: -0.1700
Data Index: 3554323 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.1975. Min Act: -0.1700
Data Index: 7663189 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.2287. Min Act: -0.1700
Data Index: 5491939 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.1975. Min Act: -0.1700
Data Index: 8801032 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.1350. Min Act: -0.1700
Data Index: 3909453 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.1350. Min Act: -0.1700
Data Index: 1241004 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.1350. Min Act: -0.1700
Data Index: 8624827 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.0725. Min Act: -0.1700
Data Index: 3346489 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.1037. Min Act: -0.1700
Data Index: 7641754 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.1037. Min Act: -0.1700
Data Index: 7039785 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.0412. Min Act: -0.1700
Data Index: 8656072 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.0412. Min Act: -0.1700
Data Index: 1968010 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.0725. Min Act: -0.1700
Data Index: 7109517 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6662. Min Range: -6.6662
Max Act: 5.9787. Min Act: -0.1700
Data Index: 6610498 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6662. Min Range: -6.6662
Max Act: 6.0100. Min Act: -0.1700
Data Index: 623135 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19