Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1720 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.2961. Min Act: -0.0001
Data Index: 1281211 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.2382. Min Act: -0.0001
Data Index: 958566 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.2517. Min Act: -0.0001
Data Index: 964158 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.2495. Min Act: -0.0001
Data Index: 1331203 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.2506. Min Act: -0.0001
Data Index: 789716 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.2041. Min Act: -0.0001
Data Index: 641444 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.1907. Min Act: -0.0001
Data Index: 889581 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.2150. Min Act: -0.0001
Data Index: 188448 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.2202. Min Act: -0.0001
Data Index: 440986 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.1667. Min Act: -0.0001
Data Index: 1276880 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.1721. Min Act: -0.0001
Data Index: 694586 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.1736. Min Act: -0.0001
Data Index: 1083704 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.1482. Min Act: -0.0001
Data Index: 853896 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.2333. Min Act: -0.0001
Data Index: 288895 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.1813. Min Act: -0.0001
Data Index: 5047 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.1752. Min Act: -0.0001
Data Index: 1312369 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.1097. Min Act: -0.0001
Data Index: 697796 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.1282. Min Act: -0.0001
Data Index: 1156138 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.1359. Min Act: -0.0001
Data Index: 1272177 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2961. Min Range: -1.2961
Max Act: 1.1967. Min Act: -0.0001
Data Index: 696845 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19