Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 8 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.2804. Min Range: -6.2804
Max Act: 6.2804. Min Act: -0.1700
Data Index: 244342 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2804. Min Range: -6.2804
Max Act: 6.2491. Min Act: -0.1700
Data Index: 862716 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2804. Min Range: -6.2804
Max Act: 6.1866. Min Act: -0.1700
Data Index: 291145 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2804. Min Range: -6.2804
Max Act: 6.0929. Min Act: -0.1700
Data Index: 755079 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.9679. Min Act: -0.1700
Data Index: 70636 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.9054. Min Act: -0.1700
Data Index: 285985 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.8429. Min Act: -0.1700
Data Index: 220549 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.9054. Min Act: -0.1700
Data Index: 689208 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.7804. Min Act: -0.1700
Data Index: 1131659 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.7804. Min Act: -0.1700
Data Index: 90504 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.6554. Min Act: -0.1700
Data Index: 158082 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.5929. Min Act: -0.1700
Data Index: 1013833 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.7804. Min Act: -0.1700
Data Index: 492494 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.6554. Min Act: -0.1700
Data Index: 407770 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.7179. Min Act: -0.1700
Data Index: 124378 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.7491. Min Act: -0.1700
Data Index: 761297 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.7491. Min Act: -0.1699
Data Index: 985440 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.6554. Min Act: -0.1700
Data Index: 1069737 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.6241. Min Act: -0.1700
Data Index: 451244 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2804. Min Range: -6.2804
Max Act: 5.6554. Min Act: -0.1700
Data Index: 350177 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19