Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2683 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1822. Min Act: -0.0001
Data Index: 189777 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1794. Min Act: -0.0001
Data Index: 443560 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1613. Min Act: -0.0001
Data Index: 186385 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1536. Min Act: -0.0001
Data Index: 1323955 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1354. Min Act: -0.0001
Data Index: 559794 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1314. Min Act: -0.0001
Data Index: 399015 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1195. Min Act: -0.0001
Data Index: 81848 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1283. Min Act: -0.0001
Data Index: 126838 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1341. Min Act: -0.0001
Data Index: 1138327 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1288. Min Act: -0.0001
Data Index: 695717 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1313. Min Act: -0.0001
Data Index: 580760 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1323. Min Act: -0.0001
Data Index: 61513 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1183. Min Act: -0.0001
Data Index: 407589 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1364. Min Act: -0.0001
Data Index: 15796 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1319. Min Act: -0.0001
Data Index: 1547963 (Python Code)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1414. Min Act: -0.0001
Data Index: 805611 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1300. Min Act: -0.0001
Data Index: 1462455 (Python Code)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1353. Min Act: -0.0001
Data Index: 254946 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1239. Min Act: -0.0001
Data Index: 325547 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1822. Min Range: -0.1822
Max Act: 0.1245. Min Act: -0.0001
Data Index: 196525 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19