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

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

Neuron 2105 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.6856. Min Act: -0.0001

Data Index: 145212 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.7205. Min Act: -0.0001

Data Index: 1259011 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.6823. Min Act: -0.0001

Data Index: 835204 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.5880. Min Act: -0.0001

Data Index: 1183631 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.4593. Min Act: -0.0001

Data Index: 1900 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.4703. Min Act: -0.0001

Data Index: 1252678 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.4097. Min Act: -0.0001

Data Index: 140727 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.3914. Min Act: -0.0002

Data Index: 930570 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.4232. Min Act: -0.0001

Data Index: 848647 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.3342. Min Act: -0.0002

Data Index: 35933 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2996. Min Act: -0.0001

Data Index: 330102 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.3183. Min Act: -0.0001

Data Index: 1019715 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2335. Min Act: -0.0001

Data Index: 353203 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2335. Min Act: -0.0001

Data Index: 1153429 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2193. Min Act: -0.0001

Data Index: 591521 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2141. Min Act: -0.0001

Data Index: 60447 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.1779. Min Act: -0.0001

Data Index: 839195 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.3156. Min Act: -0.0001

Data Index: 868722 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.1630. Min Act: -0.0001

Data Index: 718470 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.1614. Min Act: -0.0001

Data Index: 460187 (C4 (Web Text))

Max Activating Token Index: 700