Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4117 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2625. Min Act: -0.0001

Data Index: 481490 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.3732. Min Act: -0.0001

Data Index: 813580 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.4177. Min Act: -0.0001

Data Index: 919758 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.3117. Min Act: -0.0001

Data Index: 611234 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2751. Min Act: -0.0001

Data Index: 979732 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.3239. Min Act: -0.0001

Data Index: 1256178 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.3195. Min Act: -0.0001

Data Index: 350939 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.3933. Min Act: -0.0001

Data Index: 538022 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1964. Min Act: -0.0001

Data Index: 564108 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2288. Min Act: -0.0001

Data Index: 924975 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1874. Min Act: -0.0001

Data Index: 585689 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1821. Min Act: -0.0001

Data Index: 711564 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2260. Min Act: -0.0001

Data Index: 85848 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1385. Min Act: -0.0001

Data Index: 1113585 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1943. Min Act: -0.0001

Data Index: 1069244 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1959. Min Act: -0.0001

Data Index: 261526 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1107. Min Act: -0.0001

Data Index: 820844 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1303. Min Act: -0.0001

Data Index: 331803 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1157. Min Act: -0.0001

Data Index: 1213925 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.0440. Min Act: -0.0001

Data Index: 488393 (C4 (Web Text))

Max Activating Token Index: 324