Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2640 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1621. Min Act: -0.0001
Data Index: 77592 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1418. Min Act: -0.0001
Data Index: 1113598 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1348. Min Act: -0.0001
Data Index: 677685 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1282. Min Act: -0.0001
Data Index: 1211425 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1304. Min Act: -0.0001
Data Index: 93706 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1262. Min Act: -0.0001
Data Index: 292447 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1138. Min Act: -0.0001
Data Index: 210607 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1219. Min Act: -0.0001
Data Index: 674453 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1070. Min Act: -0.0001
Data Index: 484049 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1190. Min Act: -0.0001
Data Index: 427145 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1136. Min Act: -0.0001
Data Index: 152720 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1208. Min Act: -0.0001
Data Index: 1351609 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1130. Min Act: -0.0001
Data Index: 901489 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1167. Min Act: -0.0001
Data Index: 817509 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1153. Min Act: -0.0001
Data Index: 990840 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1112. Min Act: -0.0001
Data Index: 952759 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1132. Min Act: -0.0001
Data Index: 1497443 (Python Code)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1090. Min Act: -0.0001
Data Index: 896382 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1195. Min Act: -0.0001
Data Index: 1069380 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1621. Min Range: -0.1621
Max Act: 0.1093. Min Act: -0.0001
Data Index: 936914 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19