Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1008 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3131. Min Range: -5.3131
Max Act: 5.3131. Min Act: -0.1700
Data Index: 5447426 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3131. Min Range: -5.3131
Max Act: 5.0631. Min Act: -0.1700
Data Index: 2274338 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3131. Min Range: -5.3131
Max Act: 5.0006. Min Act: -0.1700
Data Index: 4149986 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.9694. Min Act: -0.1700
Data Index: 6297564 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.9069. Min Act: -0.1700
Data Index: 4287237 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.9381. Min Act: -0.1700
Data Index: 7072963 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.9069. Min Act: -0.1700
Data Index: 8754384 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.9069. Min Act: -0.1700
Data Index: 3807314 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.9069. Min Act: -0.1700
Data Index: 2490670 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.9069. Min Act: -0.1700
Data Index: 3986987 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.9069. Min Act: -0.1700
Data Index: 3042811 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.8756. Min Act: -0.1700
Data Index: 4411912 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.8756. Min Act: -0.1700
Data Index: 1002804 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.8756. Min Act: -0.1700
Data Index: 4948429 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.8131. Min Act: -0.1700
Data Index: 6204824 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.8444. Min Act: -0.1700
Data Index: 7481653 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.8131. Min Act: -0.1700
Data Index: 6477641 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.8444. Min Act: -0.1700
Data Index: 6678046 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.8444. Min Act: -0.1700
Data Index: 1795488 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3131. Min Range: -5.3131
Max Act: 4.8444. Min Act: -0.1700
Data Index: 2918081 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19