Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4458 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.9331. Min Act: -0.0001
Data Index: 259200 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.8249. Min Act: -0.0001
Data Index: 977112 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.8256. Min Act: -0.0001
Data Index: 1021405 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.9628. Min Act: -0.0001
Data Index: 918067 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.7088. Min Act: -0.0001
Data Index: 500502 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.7204. Min Act: -0.0001
Data Index: 670433 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.7126. Min Act: -0.0001
Data Index: 1079200 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.6364. Min Act: -0.0001
Data Index: 453094 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.8302. Min Act: -0.0001
Data Index: 1163566 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.6266. Min Act: -0.0001
Data Index: 187322 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.5025. Min Act: -0.0001
Data Index: 718708 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.6070. Min Act: -0.0001
Data Index: 1144414 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.6153. Min Act: -0.0001
Data Index: 602778 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.5226. Min Act: -0.0001
Data Index: 696078 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.6108. Min Act: -0.0001
Data Index: 821018 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.7538. Min Act: -0.0001
Data Index: 810608 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.4534. Min Act: -0.0001
Data Index: 85653 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.6918. Min Act: -0.0001
Data Index: 943207 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.5520. Min Act: -0.0001
Data Index: 108323 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9628. Min Range: -2.9628
Max Act: 2.6609. Min Act: -0.0001
Data Index: 379069 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19