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

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

Neuron 1976 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3744. Min Act: -0.0001

Data Index: 709426 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3527. Min Act: -0.0001

Data Index: 442449 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3422. Min Act: -0.0002

Data Index: 1148694 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3046. Min Act: -0.0002

Data Index: 871717 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2713. Min Act: -0.0002

Data Index: 715340 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2740. Min Act: -0.0002

Data Index: 464289 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2632. Min Act: -0.0002

Data Index: 1316195 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2780. Min Act: -0.0002

Data Index: 1239554 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2238. Min Act: -0.0002

Data Index: 471977 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2489. Min Act: -0.0002

Data Index: 135785 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2512. Min Act: -0.0001

Data Index: 201349 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2473. Min Act: -0.0002

Data Index: 116632 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2239. Min Act: -0.0002

Data Index: 712511 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2223. Min Act: -0.0002

Data Index: 193801 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2017. Min Act: -0.0002

Data Index: 238843 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2153. Min Act: -0.0001

Data Index: 578222 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2212. Min Act: -0.0002

Data Index: 1235367 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2125. Min Act: -0.0002

Data Index: 919970 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.1964. Min Act: -0.0002

Data Index: 232197 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.1886. Min Act: -0.0002

Data Index: 305492 (C4 (Web Text))

Max Activating Token Index: 126