Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5439 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.8086. Min Act: -0.0000

Data Index: 600465 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6996. Min Act: -0.0000

Data Index: 232978 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6075. Min Act: -0.0000

Data Index: 620608 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.5976. Min Act: -0.0000

Data Index: 734782 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.5528. Min Act: -0.0000

Data Index: 616836 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.5063. Min Act: -0.0000

Data Index: 195614 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.5192. Min Act: -0.0000

Data Index: 705063 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1164931 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1151994 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1267163 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.5085. Min Act: -0.0000

Data Index: 251386 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4709. Min Act: -0.0000

Data Index: 764919 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1343507 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1025301 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1087905 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4431. Min Act: -0.0000

Data Index: 259985 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1047490 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4473. Min Act: -0.0000

Data Index: 802776 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4448. Min Act: -0.0000

Data Index: 295854 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.4408. Min Act: -0.0000

Data Index: 576616 (C4 (Web Text))

Max Activating Token Index: 958