Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2386 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1518. Min Act: -0.0001
Data Index: 341275 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1389. Min Act: -0.0001
Data Index: 208879 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1454. Min Act: -0.0001
Data Index: 51166 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1424. Min Act: -0.0000
Data Index: 1287330 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1399. Min Act: -0.0001
Data Index: 108077 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1227. Min Act: -0.0001
Data Index: 1002570 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1211. Min Act: -0.0001
Data Index: 335187 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1316. Min Act: -0.0001
Data Index: 1500275 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1258. Min Act: -0.0001
Data Index: 866114 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1122. Min Act: -0.0001
Data Index: 1117027 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1224. Min Act: -0.0001
Data Index: 502240 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1235. Min Act: -0.0001
Data Index: 1370514 (Python Code)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1185. Min Act: -0.0001
Data Index: 276133 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1037. Min Act: -0.0001
Data Index: 993816 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1201. Min Act: -0.0001
Data Index: 442543 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1099. Min Act: -0.0001
Data Index: 664191 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1077. Min Act: -0.0001
Data Index: 376477 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1113. Min Act: -0.0001
Data Index: 887371 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1156. Min Act: -0.0001
Data Index: 356727 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1518. Min Range: -0.1518
Max Act: 0.1103. Min Act: -0.0001
Data Index: 1233502 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19