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

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

Neuron 2309 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0860. Min Range: -1.0860

Max Act: 1.0860. Min Act: -0.0001

Data Index: 371548 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.7576. Min Act: -0.0001

Data Index: 911302 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.7465. Min Act: -0.0001

Data Index: 416853 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.7143. Min Act: -0.0001

Data Index: 341026 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.5851. Min Act: -0.0001

Data Index: 525390 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.5352. Min Act: -0.0001

Data Index: 1296324 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.6177. Min Act: -0.0001

Data Index: 533621 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.6323. Min Act: -0.0001

Data Index: 303001 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.5146. Min Act: -0.0001

Data Index: 80923 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.5452. Min Act: -0.0001

Data Index: 587775 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.5042. Min Act: -0.0001

Data Index: 730838 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.5341. Min Act: -0.0001

Data Index: 518133 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.4223. Min Act: -0.0001

Data Index: 506053 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.4031. Min Act: -0.0001

Data Index: 1264522 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.3873. Min Act: -0.0001

Data Index: 673505 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.3981. Min Act: -0.0001

Data Index: 650178 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.4229. Min Act: -0.0001

Data Index: 266616 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.4256. Min Act: -0.0001

Data Index: 1320217 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.4617. Min Act: -0.0001

Data Index: 82586 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 1.0860. Min Range: -1.0860

Max Act: 0.4213. Min Act: -0.0001

Data Index: 699044 (C4 (Web Text))

Max Activating Token Index: 1022