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

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

Neuron 1104 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.9536. Min Act: -0.0000

Data Index: 1163362 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.6524. Min Act: 0.0000

Data Index: 1215927 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.3070. Min Act: -0.0000

Data Index: 19274 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.2781. Min Act: -0.0000

Data Index: 442265 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1259348 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.3529. Min Act: 0.0000

Data Index: 1289207 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.3383. Min Act: -0.0000

Data Index: 1045493 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1160290 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.1176. Min Act: 0.0000

Data Index: 768442 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1337484 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.0349. Min Act: -0.0000

Data Index: 170761 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.0419. Min Act: -0.0000

Data Index: 1264370 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.0275. Min Act: -0.0000

Data Index: 315213 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 1.9536. Min Range: -1.9536

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1135028 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.0260. Min Act: 0.0000

Data Index: 780474 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.0980. Min Act: -0.0000

Data Index: 462844 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 1.9536. Min Range: -1.9536

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1645309 (Python Code)

Max Activating Token Index: 278

Text #17

Max Range: 1.9536. Min Range: -1.9536

Max Act: 0.9479. Min Act: -0.0000

Data Index: 1012271 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.0155. Min Act: -0.0000

Data Index: 535433 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 1.9536. Min Range: -1.9536

Max Act: 0.9540. Min Act: -0.0000

Data Index: 73652 (C4 (Web Text))

Max Activating Token Index: 890