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

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

Neuron 1975 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.5692. Min Act: -0.0001

Data Index: 1256569 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.5852. Min Act: -0.0001

Data Index: 149878 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4729. Min Act: -0.0001

Data Index: 936164 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4656. Min Act: -0.0001

Data Index: 897569 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4435. Min Act: -0.0001

Data Index: 313525 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4681. Min Act: -0.0001

Data Index: 1237556 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4358. Min Act: -0.0001

Data Index: 1038874 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4450. Min Act: -0.0001

Data Index: 1339827 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4324. Min Act: -0.0001

Data Index: 1141324 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4177. Min Act: -0.0001

Data Index: 1227256 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4132. Min Act: -0.0001

Data Index: 1143438 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4234. Min Act: -0.0001

Data Index: 5255 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4111. Min Act: -0.0001

Data Index: 438398 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4254. Min Act: -0.0001

Data Index: 312218 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3985. Min Act: -0.0001

Data Index: 347728 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4111. Min Act: -0.0001

Data Index: 644451 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3726. Min Act: -0.0001

Data Index: 1179659 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4346. Min Act: -0.0001

Data Index: 39868 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3900. Min Act: -0.0001

Data Index: 1296774 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3455. Min Act: -0.0001

Data Index: 435765 (C4 (Web Text))

Max Activating Token Index: 955