Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 167 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4992. Min Act: -0.0000

Data Index: 838887 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4893. Min Act: -0.0000

Data Index: 692758 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4556. Min Act: 0.0000

Data Index: 786153 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1035824 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4525. Min Act: -0.0000

Data Index: 319246 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3885. Min Act: -0.0000

Data Index: 227839 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4001. Min Act: -0.0000

Data Index: 629833 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3947. Min Act: -0.0000

Data Index: 986706 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1280292 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1305026 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3550. Min Act: 0.0000

Data Index: 479641 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1336677 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1012495 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3342. Min Act: -0.0000

Data Index: 871773 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1296720 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3082. Min Act: -0.0000

Data Index: 766348 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.2956. Min Act: -0.0000

Data Index: 148327 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3164. Min Act: -0.0000

Data Index: 472170 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3167. Min Act: 0.0001

Data Index: 280268 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1238894 (C4 (Web Text))

Max Activating Token Index: 340