Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2449 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5735. Min Range: -2.5735

Max Act: 2.5735. Min Act: -0.0000

Data Index: 411582 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 2.5735. Min Range: -2.5735

Max Act: 2.0749. Min Act: -0.0000

Data Index: 1181615 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.6773. Min Act: -0.0000

Data Index: 105421 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 2.5735. Min Range: -2.5735

Max Act: 2.0695. Min Act: -0.0000

Data Index: 923707 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.9164. Min Act: -0.0000

Data Index: 937760 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.7843. Min Act: -0.0000

Data Index: 1482477 (Python Code)

Max Activating Token Index: 616

Text #6

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.8443. Min Act: -0.0000

Data Index: 494468 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.9292. Min Act: -0.0000

Data Index: 562199 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.7685. Min Act: -0.0000

Data Index: 1548636 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.7449. Min Act: -0.0000

Data Index: 1590281 (Python Code)

Max Activating Token Index: 851

Text #10

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.7900. Min Act: -0.0000

Data Index: 1503792 (Python Code)

Max Activating Token Index: 127

Text #11

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.6755. Min Act: -0.0000

Data Index: 840158 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.8926. Min Act: -0.0000

Data Index: 236945 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.7648. Min Act: -0.0000

Data Index: 1593531 (Python Code)

Max Activating Token Index: 451

Text #14

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.8722. Min Act: -0.0000

Data Index: 362045 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.8268. Min Act: -0.0000

Data Index: 1606878 (Python Code)

Max Activating Token Index: 480

Text #16

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.7235. Min Act: -0.0000

Data Index: 761036 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.6616. Min Act: -0.0000

Data Index: 1421296 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.6208. Min Act: -0.0000

Data Index: 1444536 (Python Code)

Max Activating Token Index: 267

Text #19

Max Range: 2.5735. Min Range: -2.5735

Max Act: 1.8154. Min Act: -0.0000

Data Index: 1573150 (Python Code)

Max Activating Token Index: 249