Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1402 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4396. Min Range: -2.4396

Max Act: 2.4396. Min Act: -0.0000

Data Index: 888883 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 2.4396. Min Range: -2.4396

Max Act: 2.3003. Min Act: -0.0000

Data Index: 1321967 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 2.4396. Min Range: -2.4396

Max Act: 2.1209. Min Act: -0.0000

Data Index: 1180881 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 2.4396. Min Range: -2.4396

Max Act: 2.2162. Min Act: -0.0000

Data Index: 1041079 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 2.4396. Min Range: -2.4396

Max Act: 2.1220. Min Act: -0.0000

Data Index: 226712 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.7867. Min Act: -0.0000

Data Index: 1280001 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.9906. Min Act: -0.0000

Data Index: 38559 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.8293. Min Act: -0.0000

Data Index: 1155159 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.8335. Min Act: -0.0000

Data Index: 487093 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.8207. Min Act: -0.0000

Data Index: 346153 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.6744. Min Act: -0.0000

Data Index: 421830 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.8133. Min Act: -0.0000

Data Index: 1359065 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.6982. Min Act: -0.0000

Data Index: 1169752 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.6792. Min Act: -0.0000

Data Index: 412215 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.6846. Min Act: -0.0000

Data Index: 176475 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.6232. Min Act: -0.0000

Data Index: 1352920 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.3822. Min Act: -0.0000

Data Index: 436950 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.5000. Min Act: -0.0000

Data Index: 216527 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.4607. Min Act: -0.0000

Data Index: 465222 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 2.4396. Min Range: -2.4396

Max Act: 1.3073. Min Act: -0.0000

Data Index: 911970 (C4 (Web Text))

Max Activating Token Index: 367