Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2204 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1495721 (Python Code)

Max Activating Token Index: 887

Text #1

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1270401 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0192. Min Act: -0.0003

Data Index: 242630 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1538125 (Python Code)

Max Activating Token Index: 256

Text #4

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1000955 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0176. Min Act: -0.0003

Data Index: 413034 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0173. Min Act: -0.0003

Data Index: 310097 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0170. Min Act: -0.0003

Data Index: 823671 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1262125 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0174. Min Act: -0.0003

Data Index: 569100 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0177. Min Act: -0.0003

Data Index: 476754 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0162. Min Act: -0.0003

Data Index: 922566 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0170. Min Act: -0.0003

Data Index: 26877 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1089264 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0176. Min Act: -0.0003

Data Index: 482121 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1371005 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0175. Min Act: -0.0003

Data Index: 300372 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1478203 (Python Code)

Max Activating Token Index: 703

Text #18

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0166. Min Act: -0.0003

Data Index: 370038 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0146. Min Act: -0.0003

Data Index: 48054 (C4 (Web Text))

Max Activating Token Index: 430