Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4191 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0656. Min Act: -0.0001
Data Index: 921981 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.1316. Min Act: -0.0001
Data Index: 975772 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0273. Min Act: -0.0001
Data Index: 719760 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0535. Min Act: -0.0001
Data Index: 916119 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.9587. Min Act: -0.0001
Data Index: 1074607 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0256. Min Act: -0.0001
Data Index: 668842 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.9877. Min Act: -0.0001
Data Index: 1243509 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.9727. Min Act: -0.0001
Data Index: 1320493 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.9450. Min Act: -0.0001
Data Index: 866733 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.8472. Min Act: -0.0001
Data Index: 85387 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.8303. Min Act: -0.0001
Data Index: 431613 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.9103. Min Act: -0.0001
Data Index: 1121463 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.7838. Min Act: -0.0001
Data Index: 1300409 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.9671. Min Act: -0.0001
Data Index: 1285275 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.7732. Min Act: -0.0001
Data Index: 1246676 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.7521. Min Act: -0.0001
Data Index: 453268 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.7527. Min Act: -0.0001
Data Index: 217406 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.9381. Min Act: -0.0001
Data Index: 290366 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.8379. Min Act: -0.0001
Data Index: 159637 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1316. Min Range: -2.1316
Max Act: 1.8311. Min Act: -0.0001
Data Index: 1151043 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19