Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2958 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2092. Min Range: -2.2092
Max Act: 2.2092. Min Act: -0.0001
Data Index: 61409 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.7553. Min Act: -0.0001
Data Index: 348183 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.6326. Min Act: -0.0001
Data Index: 609988 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.6637. Min Act: -0.0001
Data Index: 1318516 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.5198. Min Act: -0.0001
Data Index: 211153 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.5075. Min Act: -0.0001
Data Index: 471831 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.5662. Min Act: -0.0001
Data Index: 44014 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.4982. Min Act: -0.0001
Data Index: 154683 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.4901. Min Act: -0.0001
Data Index: 576984 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.3948. Min Act: -0.0001
Data Index: 606904 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.3353. Min Act: -0.0001
Data Index: 654176 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.3971. Min Act: -0.0001
Data Index: 714026 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.3189. Min Act: -0.0002
Data Index: 543619 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.2480. Min Act: -0.0001
Data Index: 255655 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.2101. Min Act: -0.0002
Data Index: 992373 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.2821. Min Act: -0.0001
Data Index: 871918 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.1785. Min Act: -0.0001
Data Index: 37220 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.1630. Min Act: -0.0001
Data Index: 921492 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.2637. Min Act: -0.0001
Data Index: 976064 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2092. Min Range: -2.2092
Max Act: 1.2635. Min Act: -0.0001
Data Index: 334338 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19