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

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

Neuron 3784 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: 1.4726. Min Range: -1.4726

Max Act: 1.4726. Min Act: -0.0000

Data Index: 1040994 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.0154. Min Act: -0.0000

Data Index: 872006 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.0932. Min Act: -0.0000

Data Index: 778680 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1103. Min Act: -0.0000

Data Index: 226342 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1346015 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1335810 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1021795 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.9226. Min Act: -0.0000

Data Index: 556104 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.8359. Min Act: -0.0000

Data Index: 573246 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.7534. Min Act: -0.0000

Data Index: 609369 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.7706. Min Act: -0.0000

Data Index: 821117 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.7704. Min Act: -0.0000

Data Index: 208527 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.8564. Min Act: -0.0000

Data Index: 89722 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.7273. Min Act: -0.0000

Data Index: 478643 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.6485. Min Act: -0.0000

Data Index: 675379 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.8215. Min Act: -0.0000

Data Index: 674245 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.6867. Min Act: -0.0000

Data Index: 951471 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1631097 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.7895. Min Act: -0.0000

Data Index: 39205 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.4726. Min Range: -1.4726

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1152073 (C4 (Web Text))

Max Activating Token Index: 451