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

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

Neuron 5829 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7142. Min Range: -4.7142

Max Act: 4.7142. Min Act: -0.0000

Data Index: 850845 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 4.7142. Min Range: -4.7142

Max Act: 3.4840. Min Act: -0.0000

Data Index: 1060589 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 4.7142. Min Range: -4.7142

Max Act: 3.2205. Min Act: -0.0000

Data Index: 117559 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 4.7142. Min Range: -4.7142

Max Act: 3.1872. Min Act: -0.0000

Data Index: 866499 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 4.7142. Min Range: -4.7142

Max Act: 3.3070. Min Act: -0.0000

Data Index: 743271 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.9793. Min Act: -0.0000

Data Index: 404643 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 4.7142. Min Range: -4.7142

Max Act: 3.4530. Min Act: -0.0000

Data Index: 855189 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.9421. Min Act: -0.0000

Data Index: 280532 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.6751. Min Act: -0.0000

Data Index: 1171886 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.9713. Min Act: -0.0000

Data Index: 811012 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.8131. Min Act: -0.0000

Data Index: 820607 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.3191. Min Act: -0.0000

Data Index: 255793 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.5097. Min Act: -0.0000

Data Index: 638929 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.2440. Min Act: -0.0000

Data Index: 66234 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.3446. Min Act: -0.0000

Data Index: 1256986 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.2146. Min Act: -0.0000

Data Index: 916732 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.2820. Min Act: -0.0000

Data Index: 121406 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.2600. Min Act: -0.0000

Data Index: 594876 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.3011. Min Act: -0.0000

Data Index: 289465 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 4.7142. Min Range: -4.7142

Max Act: 2.4126. Min Act: -0.0000

Data Index: 87104 (C4 (Web Text))

Max Activating Token Index: 858