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

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

Neuron 548 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1292100 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5422. Min Act: -0.0000

Data Index: 820555 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5163. Min Act: -0.0000

Data Index: 320383 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4254. Min Act: -0.0000

Data Index: 172424 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1121823 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4632. Min Act: -0.0000

Data Index: 892896 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4407. Min Act: -0.0000

Data Index: 500711 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4471. Min Act: -0.0000

Data Index: 53486 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4249. Min Act: -0.0000

Data Index: 193423 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4477. Min Act: -0.0000

Data Index: 330398 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1303296 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3898. Min Act: -0.0000

Data Index: 548602 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1069207 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1106256 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4024. Min Act: -0.0000

Data Index: 5746 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3731. Min Act: -0.0000

Data Index: 517629 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3735. Min Act: -0.0000

Data Index: 632295 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3710. Min Act: -0.0000

Data Index: 378315 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3985. Min Act: -0.0000

Data Index: 312233 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3751. Min Act: -0.0000

Data Index: 199842 (C4 (Web Text))

Max Activating Token Index: 889