Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6076 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1805. Min Act: -0.0001
Data Index: 123241 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1673. Min Act: -0.0001
Data Index: 570777 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1710. Min Act: -0.0001
Data Index: 171227 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1627. Min Act: -0.0001
Data Index: 556958 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1408. Min Act: -0.0001
Data Index: 949847 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1697. Min Act: -0.0001
Data Index: 1308946 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1237. Min Act: -0.0001
Data Index: 284336 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1467. Min Act: -0.0001
Data Index: 66988 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1394. Min Act: -0.0001
Data Index: 481287 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1577. Min Act: -0.0001
Data Index: 370763 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1375. Min Act: -0.0001
Data Index: 392004 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1615. Min Act: -0.0001
Data Index: 1007796 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1370. Min Act: -0.0001
Data Index: 914354 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1565. Min Act: -0.0001
Data Index: 1289239 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1525. Min Act: -0.0001
Data Index: 1002197 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1335. Min Act: -0.0001
Data Index: 1548335 (Python Code)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1277. Min Act: -0.0001
Data Index: 383260 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1536. Min Act: -0.0001
Data Index: 1218339 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1486. Min Act: -0.0001
Data Index: 449421 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1805. Min Range: -0.1805
Max Act: 0.1416. Min Act: -0.0001
Data Index: 1458358 (Python Code)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19