Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2931 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.6334. Min Act: -0.0001
Data Index: 834001 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.6564. Min Act: -0.0001
Data Index: 778427 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.4453. Min Act: -0.0001
Data Index: 1028823 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.4073. Min Act: -0.0001
Data Index: 611943 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.4623. Min Act: -0.0001
Data Index: 222803 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.3622. Min Act: -0.0001
Data Index: 1093433 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.2928. Min Act: -0.0001
Data Index: 1125794 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.3264. Min Act: -0.0001
Data Index: 415169 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.2742. Min Act: -0.0001
Data Index: 759866 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.3244. Min Act: -0.0001
Data Index: 1199016 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.2127. Min Act: -0.0001
Data Index: 793788 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.2373. Min Act: -0.0001
Data Index: 1324001 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.2323. Min Act: -0.0001
Data Index: 726262 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.3353. Min Act: -0.0001
Data Index: 775541 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.2110. Min Act: -0.0001
Data Index: 1213801 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.1646. Min Act: -0.0001
Data Index: 1358164 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.1518. Min Act: -0.0001
Data Index: 657175 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.1569. Min Act: -0.0001
Data Index: 93577 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.1187. Min Act: -0.0001
Data Index: 104334 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6564. Min Range: -1.6564
Max Act: 1.2137. Min Act: -0.0001
Data Index: 321743 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19