Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.3600. Min Act: -0.1700
Data Index: 2219422 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.2037. Min Act: -0.1700
Data Index: 7544381 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.1725. Min Act: -0.1700
Data Index: 831371 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0475. Min Act: -0.1700
Data Index: 2554689 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0475. Min Act: -0.1700
Data Index: 4485570 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0162. Min Act: -0.1700
Data Index: 3419246 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0162. Min Act: -0.1700
Data Index: 4810409 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.9850. Min Act: -0.1700
Data Index: 1156598 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.9850. Min Act: -0.1700
Data Index: 887962 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.9850. Min Act: -0.1700
Data Index: 1823441 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.9850. Min Act: -0.1700
Data Index: 5760630 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.9537. Min Act: -0.1700
Data Index: 2286322 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.9225. Min Act: -0.1700
Data Index: 3331210 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.9225. Min Act: -0.1700
Data Index: 8020029 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.9537. Min Act: -0.1700
Data Index: 4653810 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.9225. Min Act: -0.1700
Data Index: 5939378 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.8912. Min Act: -0.1700
Data Index: 1140891 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.8600. Min Act: -0.1700
Data Index: 5882334 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.8912. Min Act: -0.1700
Data Index: 761716 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3600. Min Range: -6.3600
Max Act: 5.8912. Min Act: -0.1700
Data Index: 3142660 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19