Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 413 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6983. Min Range: -6.6983
Max Act: 6.6983. Min Act: -0.1700
Data Index: 3719377 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6983. Min Range: -6.6983
Max Act: 6.0420. Min Act: -0.1700
Data Index: 5142378 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6983. Min Range: -6.6983
Max Act: 6.0420. Min Act: -0.1700
Data Index: 6217186 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.9795. Min Act: -0.1700
Data Index: 313455 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.9795. Min Act: -0.1700
Data Index: 3599934 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.9170. Min Act: -0.1700
Data Index: 4976104 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.9170. Min Act: -0.1700
Data Index: 2146796 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.9170. Min Act: -0.1700
Data Index: 8758757 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.8858. Min Act: -0.1700
Data Index: 2825129 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.8858. Min Act: -0.1700
Data Index: 504865 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.8858. Min Act: -0.1700
Data Index: 4212395 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.8545. Min Act: -0.1700
Data Index: 7248655 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.8233. Min Act: -0.1700
Data Index: 5302654 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.8233. Min Act: -0.1700
Data Index: 1608059 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.7920. Min Act: -0.1700
Data Index: 345665 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.7920. Min Act: -0.1700
Data Index: 7651584 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.7608. Min Act: -0.1700
Data Index: 2076346 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.7295. Min Act: -0.1700
Data Index: 1781863 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.6983. Min Act: -0.1700
Data Index: 3606751 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6983. Min Range: -6.6983
Max Act: 5.6983. Min Act: -0.1700
Data Index: 5830749 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19