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

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

Neuron 2406 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3354. Min Act: -0.0001

Data Index: 466024 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3490. Min Act: -0.0001

Data Index: 834315 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3299. Min Act: -0.0001

Data Index: 688933 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3197. Min Act: -0.0001

Data Index: 868649 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3092. Min Act: -0.0001

Data Index: 170986 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2966. Min Act: -0.0001

Data Index: 824188 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1231622 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2941. Min Act: -0.0001

Data Index: 386607 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3172. Min Act: -0.0001

Data Index: 202039 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3166. Min Act: -0.0001

Data Index: 827443 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3073. Min Act: -0.0001

Data Index: 1029518 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3035. Min Act: -0.0001

Data Index: 818264 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3230. Min Act: -0.0001

Data Index: 151621 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3147. Min Act: -0.0001

Data Index: 150321 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2898. Min Act: -0.0001

Data Index: 326232 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3107. Min Act: -0.0001

Data Index: 1336914 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3090. Min Act: -0.0001

Data Index: 368931 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2854. Min Act: -0.0001

Data Index: 654109 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3051. Min Act: -0.0001

Data Index: 1077704 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2860. Min Act: -0.0001

Data Index: 114134 (C4 (Web Text))

Max Activating Token Index: 768