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

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

Neuron 390 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: 0.4962. Min Range: -0.4962

Max Act: 0.4925. Min Act: -0.0001

Data Index: 225716 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4732. Min Act: -0.0001

Data Index: 385408 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4962. Min Act: -0.0000

Data Index: 43254 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1304286 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4417. Min Act: -0.0001

Data Index: 1144439 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4151. Min Act: -0.0001

Data Index: 860182 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4269. Min Act: -0.0000

Data Index: 827271 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4415. Min Act: -0.0001

Data Index: 142758 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1320220 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4013. Min Act: -0.0001

Data Index: 1221103 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3827. Min Act: -0.0001

Data Index: 1226101 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4234. Min Act: -0.0001

Data Index: 255744 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4200. Min Act: -0.0000

Data Index: 417838 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4118. Min Act: -0.0001

Data Index: 57233 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3622. Min Act: -0.0001

Data Index: 1235797 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4158. Min Act: -0.0001

Data Index: 849944 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3996. Min Act: -0.0001

Data Index: 572048 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4132. Min Act: -0.0001

Data Index: 363855 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3977. Min Act: -0.0001

Data Index: 672675 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3843. Min Act: -0.0001

Data Index: 409174 (C4 (Web Text))

Max Activating Token Index: 934