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

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

Neuron 3746 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8163. Min Act: -0.0001

Data Index: 489389 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8890. Min Act: -0.0001

Data Index: 890039 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.6641. Min Act: -0.0000

Data Index: 1324724 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.6901. Min Act: -0.0001

Data Index: 1128918 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.6455. Min Act: -0.0001

Data Index: 516010 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.6830. Min Act: -0.0000

Data Index: 1073841 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.5767. Min Act: -0.0001

Data Index: 273728 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.6127. Min Act: -0.0001

Data Index: 978092 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.5527. Min Act: -0.0001

Data Index: 667275 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.4038. Min Act: -0.0001

Data Index: 987248 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.4445. Min Act: -0.0001

Data Index: 1332144 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.4422. Min Act: -0.0001

Data Index: 193315 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.4827. Min Act: -0.0001

Data Index: 527824 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.3965. Min Act: -0.0001

Data Index: 569199 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.4360. Min Act: -0.0001

Data Index: 990436 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.3852. Min Act: -0.0000

Data Index: 726403 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.4268. Min Act: -0.0001

Data Index: 395428 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.4551. Min Act: -0.0001

Data Index: 1104105 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.4590. Min Act: -0.0001

Data Index: 442223 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.3203. Min Act: -0.0000

Data Index: 1201651 (C4 (Web Text))

Max Activating Token Index: 736