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

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

Neuron 3956 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3164. Min Range: -1.3164

Max Act: 1.3164. Min Act: -0.0001

Data Index: 212567 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 1.3164. Min Range: -1.3164

Max Act: 1.2168. Min Act: -0.0001

Data Index: 317829 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.9862. Min Act: -0.0001

Data Index: 98416 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.9768. Min Act: -0.0001

Data Index: 121159 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.9174. Min Act: -0.0001

Data Index: 1018851 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.8857. Min Act: -0.0001

Data Index: 184172 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.8071. Min Act: -0.0001

Data Index: 660879 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.8354. Min Act: -0.0001

Data Index: 671993 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.8296. Min Act: -0.0001

Data Index: 1121321 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.7204. Min Act: -0.0001

Data Index: 926193 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.8376. Min Act: -0.0001

Data Index: 393158 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.7513. Min Act: -0.0001

Data Index: 419820 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.7733. Min Act: -0.0001

Data Index: 389783 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.7760. Min Act: -0.0000

Data Index: 49710 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.7967. Min Act: -0.0001

Data Index: 129554 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.7276. Min Act: -0.0001

Data Index: 15234 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.7135. Min Act: -0.0001

Data Index: 1115963 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.7773. Min Act: -0.0001

Data Index: 542931 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.7844. Min Act: -0.0001

Data Index: 1173175 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 1.3164. Min Range: -1.3164

Max Act: 0.7116. Min Act: -0.0001

Data Index: 241380 (C4 (Web Text))

Max Activating Token Index: 1016