Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3862 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.6462. Min Act: -0.0001

Data Index: 591805 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.4820. Min Act: -0.0001

Data Index: 106261 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.4127. Min Act: -0.0001

Data Index: 974813 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.3928. Min Act: -0.0001

Data Index: 45346 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.3708. Min Act: -0.0001

Data Index: 547855 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.2646. Min Act: -0.0001

Data Index: 1090610 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.3043. Min Act: -0.0001

Data Index: 1511705 (Python Code)

Max Activating Token Index: 612

Text #7

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.4432. Min Act: -0.0001

Data Index: 268225 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.2104. Min Act: -0.0001

Data Index: 1090233 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.2561. Min Act: -0.0001

Data Index: 1503890 (Python Code)

Max Activating Token Index: 572

Text #10

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.2805. Min Act: -0.0001

Data Index: 1407713 (Python Code)

Max Activating Token Index: 996

Text #11

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.2154. Min Act: -0.0001

Data Index: 1353628 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.1292. Min Act: -0.0001

Data Index: 29250 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.1669. Min Act: -0.0001

Data Index: 226071 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.1480. Min Act: -0.0001

Data Index: 1835 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.2231. Min Act: -0.0001

Data Index: 1092293 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.2104. Min Act: -0.0001

Data Index: 1197119 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.0629. Min Act: -0.0001

Data Index: 1136871 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.2163. Min Act: -0.0001

Data Index: 640784 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 1.6462. Min Range: -1.6462

Max Act: 1.0321. Min Act: -0.0001

Data Index: 153869 (C4 (Web Text))

Max Activating Token Index: 677