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

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

Neuron 3400 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0158. Min Range: -1.0158

Max Act: 1.0158. Min Act: -0.0000

Data Index: 1542715 (Python Code)

Max Activating Token Index: 753

Text #1

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1462889 (Python Code)

Max Activating Token Index: 910

Text #2

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.9316. Min Act: -0.0000

Data Index: 632663 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8719. Min Act: -0.0000

Data Index: 744866 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8995. Min Act: -0.0000

Data Index: 863840 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1435059 (Python Code)

Max Activating Token Index: 868

Text #6

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8323. Min Act: -0.0000

Data Index: 36237 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1394270 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7864. Min Act: -0.0000

Data Index: 409900 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7988. Min Act: 0.0000

Data Index: 1296999 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1153719 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7427. Min Act: -0.0000

Data Index: 279792 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1439746 (Python Code)

Max Activating Token Index: 300

Text #13

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7671. Min Act: -0.0000

Data Index: 19708 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1546259 (Python Code)

Max Activating Token Index: 979

Text #15

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7769. Min Act: 0.0000

Data Index: 717220 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7416. Min Act: -0.0000

Data Index: 15435 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7575. Min Act: -0.0000

Data Index: 334032 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1306250 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1129171 (C4 (Web Text))

Max Activating Token Index: 747