Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2441 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.5216. Min Act: -0.0001
Data Index: 74880 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.5223. Min Act: -0.0001
Data Index: 143241 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4665. Min Act: -0.0001
Data Index: 1196114 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.5219. Min Act: -0.0001
Data Index: 403161 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.5088. Min Act: -0.0001
Data Index: 794716 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.5161. Min Act: -0.0001
Data Index: 55961 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4788. Min Act: -0.0001
Data Index: 29802 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4821. Min Act: -0.0001
Data Index: 1142582 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4961. Min Act: -0.0001
Data Index: 352725 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4692. Min Act: -0.0001
Data Index: 704396 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4686. Min Act: -0.0001
Data Index: 1341493 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4741. Min Act: -0.0001
Data Index: 902830 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4770. Min Act: -0.0001
Data Index: 937680 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4870. Min Act: -0.0001
Data Index: 1337407 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4190. Min Act: -0.0001
Data Index: 830938 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4823. Min Act: -0.0001
Data Index: 531730 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4689. Min Act: -0.0001
Data Index: 456294 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4336. Min Act: -0.0001
Data Index: 779547 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4487. Min Act: -0.0001
Data Index: 418883 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5223. Min Range: -0.5223
Max Act: 0.4289. Min Act: -0.0001
Data Index: 491076 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19