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

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

Neuron 3675 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: 0.7544. Min Range: -0.7544

Max Act: 0.7544. Min Act: -0.0001

Data Index: 456157 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6990. Min Act: -0.0001

Data Index: 701051 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1326672 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.7274. Min Act: -0.0001

Data Index: 752145 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6705. Min Act: -0.0001

Data Index: 682739 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6158. Min Act: -0.0001

Data Index: 351840 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.7176. Min Act: -0.0001

Data Index: 64858 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6558. Min Act: -0.0001

Data Index: 359137 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6383. Min Act: -0.0001

Data Index: 1256702 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6539. Min Act: -0.0001

Data Index: 294460 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6226. Min Act: -0.0001

Data Index: 950369 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6953. Min Act: -0.0001

Data Index: 162555 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6790. Min Act: -0.0001

Data Index: 897616 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6453. Min Act: -0.0001

Data Index: 175484 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6833. Min Act: -0.0001

Data Index: 1027198 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6225. Min Act: -0.0001

Data Index: 568036 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6190. Min Act: -0.0001

Data Index: 1283460 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5960. Min Act: -0.0001

Data Index: 858257 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6152. Min Act: -0.0001

Data Index: 541450 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6309. Min Act: -0.0001

Data Index: 571994 (C4 (Web Text))

Max Activating Token Index: 62