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

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

Neuron 797 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2671. Min Act: -0.0001

Data Index: 535 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2305. Min Act: -0.0001

Data Index: 147804 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2386. Min Act: -0.0001

Data Index: 189694 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2378. Min Act: -0.0001

Data Index: 157486 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2160. Min Act: -0.0001

Data Index: 285429 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2294. Min Act: -0.0001

Data Index: 220536 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2307. Min Act: -0.0001

Data Index: 128315 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2041. Min Act: -0.0001

Data Index: 675525 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2341. Min Act: -0.0001

Data Index: 1256135 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2125. Min Act: -0.0001

Data Index: 1247691 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2242. Min Act: -0.0001

Data Index: 69061 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2013. Min Act: -0.0001

Data Index: 1016853 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2091. Min Act: -0.0001

Data Index: 266783 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2018. Min Act: -0.0001

Data Index: 36624 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2185. Min Act: -0.0001

Data Index: 496488 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1857. Min Act: -0.0001

Data Index: 39993 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1998. Min Act: -0.0001

Data Index: 182416 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1870. Min Act: -0.0001

Data Index: 742457 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1719. Min Act: -0.0001

Data Index: 945215 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1957. Min Act: -0.0001

Data Index: 1033978 (C4 (Web Text))

Max Activating Token Index: 880