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

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

Neuron 3770 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.4465. Min Act: -0.0000

Data Index: 917304 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2269. Min Act: -0.0000

Data Index: 1287744 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.1214. Min Act: -0.0000

Data Index: 611244 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.0464. Min Act: -0.0000

Data Index: 58057 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.0367. Min Act: -0.0000

Data Index: 50896 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.0025. Min Act: -0.0000

Data Index: 57610 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1115557 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.9118. Min Act: -0.0000

Data Index: 219415 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.8519. Min Act: -0.0000

Data Index: 905220 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.8792. Min Act: -0.0000

Data Index: 406846 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.8244. Min Act: -0.0000

Data Index: 1167913 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.8266. Min Act: -0.0000

Data Index: 891913 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.8137. Min Act: -0.0000

Data Index: 904955 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.7877. Min Act: -0.0000

Data Index: 728123 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1161831 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1039126 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.7968. Min Act: 0.0000

Data Index: 233700 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.7759. Min Act: -0.0000

Data Index: 63560 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.7690. Min Act: -0.0000

Data Index: 541011 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 1.4465. Min Range: -1.4465

Max Act: 0.7401. Min Act: -0.0000

Data Index: 539825 (C4 (Web Text))

Max Activating Token Index: 318