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

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

Neuron 6 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8059. Min Range: -3.8059

Max Act: 3.8059. Min Act: -0.0001

Data Index: 915 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 3.8059. Min Range: -3.8059

Max Act: 3.3478. Min Act: -0.0001

Data Index: 805103 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 3.8059. Min Range: -3.8059

Max Act: 3.2175. Min Act: -0.0001

Data Index: 405675 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 3.8059. Min Range: -3.8059

Max Act: 3.1286. Min Act: -0.0001

Data Index: 125925 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 3.8059. Min Range: -3.8059

Max Act: 3.2009. Min Act: -0.0001

Data Index: 1077728 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 3.8059. Min Range: -3.8059

Max Act: 3.0608. Min Act: -0.0001

Data Index: 99813 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 3.8059. Min Range: -3.8059

Max Act: 3.1379. Min Act: -0.0001

Data Index: 5736 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.7468. Min Act: -0.0001

Data Index: 1013135 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.7190. Min Act: -0.0001

Data Index: 291370 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.7949. Min Act: -0.0001

Data Index: 380005 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.7694. Min Act: -0.0001

Data Index: 911407 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.4375. Min Act: -0.0001

Data Index: 324104 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.6533. Min Act: -0.0001

Data Index: 252287 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.6368. Min Act: -0.0001

Data Index: 1051155 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.3690. Min Act: -0.0001

Data Index: 579494 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.5588. Min Act: -0.0001

Data Index: 283688 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.2653. Min Act: -0.0001

Data Index: 1046671 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.2796. Min Act: -0.0001

Data Index: 1298370 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.1997. Min Act: -0.0001

Data Index: 692532 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 3.8059. Min Range: -3.8059

Max Act: 2.5113. Min Act: -0.0001

Data Index: 1276127 (C4 (Web Text))

Max Activating Token Index: 935