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

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

Neuron 730 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3973. Min Range: -2.3973

Max Act: 2.0784. Min Act: -0.0000

Data Index: 352125 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 2.3973. Min Range: -2.3973

Max Act: 2.3039. Min Act: -0.0000

Data Index: 1125487 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 2.3973. Min Range: -2.3973

Max Act: 2.1695. Min Act: -0.0000

Data Index: 552436 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 2.3973. Min Range: -2.3973

Max Act: 2.3973. Min Act: -0.0000

Data Index: 767914 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 2.3973. Min Range: -2.3973

Max Act: 2.0816. Min Act: -0.0000

Data Index: 1022490 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 2.3973. Min Range: -2.3973

Max Act: 2.1472. Min Act: -0.0000

Data Index: 1102058 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 2.3973. Min Range: -2.3973

Max Act: 2.1277. Min Act: -0.0000

Data Index: 237815 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 2.3973. Min Range: -2.3973

Max Act: 2.1100. Min Act: -0.0000

Data Index: 670302 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 2.3973. Min Range: -2.3973

Max Act: 2.0734. Min Act: -0.0000

Data Index: 129165 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 2.3973. Min Range: -2.3973

Max Act: 1.8471. Min Act: -0.0000

Data Index: 1543420 (Python Code)

Max Activating Token Index: 335

Text #10

Max Range: 2.3973. Min Range: -2.3973

Max Act: 1.9149. Min Act: -0.0000

Data Index: 111802 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 2.3973. Min Range: -2.3973

Max Act: 1.9044. Min Act: -0.0000

Data Index: 6438 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 2.3973. Min Range: -2.3973

Max Act: 2.0210. Min Act: -0.0000

Data Index: 834972 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 2.3973. Min Range: -2.3973

Max Act: 2.0068. Min Act: -0.0000

Data Index: 492979 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 2.3973. Min Range: -2.3973

Max Act: 1.8423. Min Act: -0.0000

Data Index: 1460200 (Python Code)

Max Activating Token Index: 481

Text #15

Max Range: 2.3973. Min Range: -2.3973

Max Act: 1.9238. Min Act: -0.0000

Data Index: 132659 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 2.3973. Min Range: -2.3973

Max Act: 1.9170. Min Act: -0.0000

Data Index: 509595 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 2.3973. Min Range: -2.3973

Max Act: 1.8140. Min Act: -0.0000

Data Index: 946036 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 2.3973. Min Range: -2.3973

Max Act: 1.9109. Min Act: -0.0000

Data Index: 958057 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 2.3973. Min Range: -2.3973

Max Act: 1.9153. Min Act: -0.0000

Data Index: 1085710 (C4 (Web Text))

Max Activating Token Index: 909