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

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

Neuron 945 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8778. Min Act: -0.0002

Data Index: 1143253 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8957. Min Act: -0.0001

Data Index: 772169 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8298. Min Act: -0.0001

Data Index: 932143 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8080. Min Act: -0.0002

Data Index: 2718 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7967. Min Act: -0.0002

Data Index: 206887 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7161. Min Act: -0.0002

Data Index: 883962 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7241. Min Act: -0.0002

Data Index: 1224732 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7269. Min Act: -0.0002

Data Index: 118093 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7400. Min Act: -0.0002

Data Index: 1268256 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7175. Min Act: -0.0001

Data Index: 108888 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7114. Min Act: -0.0002

Data Index: 328225 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7474. Min Act: -0.0002

Data Index: 704577 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6905. Min Act: -0.0001

Data Index: 1060325 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7348. Min Act: -0.0001

Data Index: 518445 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6794. Min Act: -0.0001

Data Index: 1044402 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6505. Min Act: -0.0002

Data Index: 603544 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6478. Min Act: -0.0002

Data Index: 114435 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6939. Min Act: -0.0001

Data Index: 823456 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6577. Min Act: -0.0001

Data Index: 956958 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6499. Min Act: -0.0001

Data Index: 244213 (C4 (Web Text))

Max Activating Token Index: 14