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

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

Neuron 1146 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.9808. Min Act: -0.0000

Data Index: 1195271 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.8121. Min Act: -0.0000

Data Index: 317097 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.8281. Min Act: -0.0000

Data Index: 502912 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.6941. Min Act: -0.0000

Data Index: 405057 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.5969. Min Act: -0.0000

Data Index: 569984 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.5216. Min Act: -0.0000

Data Index: 528684 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.3116. Min Act: -0.0000

Data Index: 38209 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.2562. Min Act: -0.0000

Data Index: 606060 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.3665. Min Act: -0.0000

Data Index: 1135240 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.3149. Min Act: -0.0000

Data Index: 244326 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.4138. Min Act: -0.0000

Data Index: 1085242 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.4090. Min Act: -0.0000

Data Index: 684011 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.1060. Min Act: -0.0000

Data Index: 1122735 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.0638. Min Act: -0.0000

Data Index: 959174 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.0620. Min Act: -0.0000

Data Index: 37509 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 2.9808. Min Range: -2.9808

Max Act: 1.9631. Min Act: -0.0000

Data Index: 1000280 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.2451. Min Act: -0.0000

Data Index: 945543 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.1257. Min Act: -0.0000

Data Index: 1231249 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 2.9808. Min Range: -2.9808

Max Act: 2.1235. Min Act: -0.0000

Data Index: 1117516 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 2.9808. Min Range: -2.9808

Max Act: 1.9689. Min Act: -0.0000

Data Index: 172020 (C4 (Web Text))

Max Activating Token Index: 231