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

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

Neuron 3822 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.9124. Min Act: -0.0001

Data Index: 564509 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1080901 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1152139 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.9450. Min Act: -0.0000

Data Index: 627481 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1133595 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.7754. Min Act: -0.0001

Data Index: 102651 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1100907 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.7718. Min Act: -0.0000

Data Index: 745028 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.6946. Min Act: -0.0000

Data Index: 984034 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.7404. Min Act: -0.0000

Data Index: 478042 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1179148 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1153464 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1319354 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.6672. Min Act: -0.0000

Data Index: 812861 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1249641 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1275703 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.6068. Min Act: -0.0001

Data Index: 908852 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.7284. Min Act: -0.0000

Data Index: 809627 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.6192. Min Act: -0.0000

Data Index: 967740 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.9450. Min Range: -0.9450

Max Act: 0.6344. Min Act: -0.0001

Data Index: 676704 (C4 (Web Text))

Max Activating Token Index: 286