Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 808 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1358. Min Range: -4.1358
Max Act: 4.1358. Min Act: -0.1700
Data Index: 6697082 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1358. Min Range: -4.1358
Max Act: 4.1046. Min Act: -0.1700
Data Index: 6704461 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1358. Min Range: -4.1358
Max Act: 4.1046. Min Act: -0.1700
Data Index: 1209859 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9326. Min Act: -0.1700
Data Index: 60798 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9326. Min Act: -0.1700
Data Index: 2395940 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9170. Min Act: -0.1700
Data Index: 451556 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.8857. Min Act: -0.1700
Data Index: 8190672 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.8857. Min Act: -0.1700
Data Index: 7728918 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.8701. Min Act: -0.1700
Data Index: 2748552 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.8545. Min Act: -0.1700
Data Index: 5519657 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.8545. Min Act: -0.1700
Data Index: 5870830 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.8232. Min Act: -0.1700
Data Index: 4698269 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.8076. Min Act: -0.1700
Data Index: 1092933 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.7763. Min Act: -0.1700
Data Index: 7554775 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.7919. Min Act: -0.1700
Data Index: 2154680 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.7763. Min Act: -0.1700
Data Index: 2014406 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.7919. Min Act: -0.1700
Data Index: 6818124 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.7607. Min Act: -0.1700
Data Index: 4738340 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.7763. Min Act: -0.1700
Data Index: 2071381 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.7919. Min Act: -0.1700
Data Index: 734918 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19