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

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

Neuron 2346 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5750. Min Act: -0.0001

Data Index: 913448 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5135. Min Act: -0.0001

Data Index: 589874 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5243. Min Act: -0.0001

Data Index: 407174 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1290469 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5153. Min Act: -0.0001

Data Index: 1077207 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4357. Min Act: -0.0001

Data Index: 9079 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5100. Min Act: -0.0001

Data Index: 1055764 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4554. Min Act: -0.0001

Data Index: 1071694 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4740. Min Act: -0.0000

Data Index: 457088 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4581. Min Act: -0.0000

Data Index: 344458 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4361. Min Act: -0.0000

Data Index: 943082 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4639. Min Act: -0.0001

Data Index: 1271280 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4617. Min Act: -0.0001

Data Index: 789949 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1164935 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4037. Min Act: -0.0001

Data Index: 298952 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1206933 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.3968. Min Act: -0.0001

Data Index: 245502 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4356. Min Act: -0.0001

Data Index: 233487 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.3992. Min Act: -0.0001

Data Index: 429778 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.3771. Min Act: -0.0001

Data Index: 126822 (C4 (Web Text))

Max Activating Token Index: 550