Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1106 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1137412 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0665. Min Act: -0.0002

Data Index: 790656 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0624. Min Act: -0.0002

Data Index: 6629 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0640. Min Act: -0.0001

Data Index: 245190 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1316282 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1141874 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1254292 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1110178 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1271089 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0592. Min Act: -0.0002

Data Index: 939969 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0585. Min Act: -0.0002

Data Index: 552992 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1279762 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1331607 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1237884 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0588. Min Act: -0.0002

Data Index: 764027 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0588. Min Act: -0.0002

Data Index: 229702 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0579. Min Act: -0.0001

Data Index: 122128 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0564. Min Act: -0.0002

Data Index: 469676 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0561. Min Act: -0.0002

Data Index: 506221 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0562. Min Act: -0.0002

Data Index: 378191 (C4 (Web Text))

Max Activating Token Index: 1000