Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 162 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.3954. Min Act: -0.0001

Data Index: 442812 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.4061. Min Act: -0.0001

Data Index: 196179 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.3437. Min Act: -0.0001

Data Index: 284435 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.3186. Min Act: -0.0001

Data Index: 472018 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.2493. Min Act: -0.0001

Data Index: 743380 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.3650. Min Act: -0.0001

Data Index: 1522109 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.2821. Min Act: -0.0001

Data Index: 936903 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.2808. Min Act: -0.0001

Data Index: 249765 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.3056. Min Act: -0.0001

Data Index: 1022680 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.2194. Min Act: -0.0001

Data Index: 30069 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.1981. Min Act: -0.0001

Data Index: 823426 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.2174. Min Act: -0.0001

Data Index: 406645 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.2504. Min Act: -0.0001

Data Index: 1288681 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.2868. Min Act: -0.0001

Data Index: 1541473 (Python Code)

Max Activating Token Index: 627

Text #14

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.2002. Min Act: -0.0001

Data Index: 170621 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.2562. Min Act: -0.0001

Data Index: 1545610 (Python Code)

Max Activating Token Index: 435

Text #16

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.1683. Min Act: -0.0001

Data Index: 1335951 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.2333. Min Act: -0.0001

Data Index: 830033 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.1934. Min Act: -0.0001

Data Index: 922838 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 1.4061. Min Range: -1.4061

Max Act: 1.1203. Min Act: -0.0001

Data Index: 6917 (C4 (Web Text))

Max Activating Token Index: 589