Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4665 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4264. Min Range: -2.4264
Max Act: 2.4264. Min Act: -0.0001
Data Index: 744690 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4264. Min Range: -2.4264
Max Act: 2.1780. Min Act: -0.0001
Data Index: 126708 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4264. Min Range: -2.4264
Max Act: 2.0955. Min Act: -0.0001
Data Index: 383804 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4264. Min Range: -2.4264
Max Act: 2.1001. Min Act: -0.0001
Data Index: 340937 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4264. Min Range: -2.4264
Max Act: 2.1933. Min Act: -0.0001
Data Index: 826878 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4264. Min Range: -2.4264
Max Act: 2.0550. Min Act: -0.0001
Data Index: 335142 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4264. Min Range: -2.4264
Max Act: 2.0363. Min Act: -0.0001
Data Index: 1167804 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4264. Min Range: -2.4264
Max Act: 2.0803. Min Act: -0.0001
Data Index: 452032 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4264. Min Range: -2.4264
Max Act: 2.0927. Min Act: -0.0001
Data Index: 294150 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4264. Min Range: -2.4264
Max Act: 1.9844. Min Act: -0.0001
Data Index: 344842 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4264. Min Range: -2.4264
Max Act: 1.9477. Min Act: -0.0001
Data Index: 496269 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4264. Min Range: -2.4264
Max Act: 1.9241. Min Act: -0.0001
Data Index: 1506889 (Python Code)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4264. Min Range: -2.4264
Max Act: 1.9113. Min Act: -0.0001
Data Index: 178863 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4264. Min Range: -2.4264
Max Act: 1.9113. Min Act: -0.0001
Data Index: 129676 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4264. Min Range: -2.4264
Max Act: 1.7202. Min Act: -0.0001
Data Index: 503019 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4264. Min Range: -2.4264
Max Act: 1.8920. Min Act: -0.0001
Data Index: 1346792 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4264. Min Range: -2.4264
Max Act: 1.9465. Min Act: -0.0001
Data Index: 1445330 (Python Code)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4264. Min Range: -2.4264
Max Act: 1.7636. Min Act: -0.0001
Data Index: 463886 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4264. Min Range: -2.4264
Max Act: 1.8657. Min Act: -0.0001
Data Index: 945536 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4264. Min Range: -2.4264
Max Act: 1.7602. Min Act: -0.0001
Data Index: 606892 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19