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

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

Neuron 3946 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8462. Min Act: -0.0002

Data Index: 493929 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8875. Min Act: -0.0001

Data Index: 620623 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8407. Min Act: -0.0001

Data Index: 651911 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8201. Min Act: -0.0002

Data Index: 568383 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8357. Min Act: -0.0001

Data Index: 218145 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7715. Min Act: -0.0002

Data Index: 1340920 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7970. Min Act: -0.0002

Data Index: 988965 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7520. Min Act: -0.0002

Data Index: 167508 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6351. Min Act: -0.0001

Data Index: 138418 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7377. Min Act: -0.0002

Data Index: 51728 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6600. Min Act: -0.0001

Data Index: 284332 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7464. Min Act: -0.0001

Data Index: 724908 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6694. Min Act: -0.0001

Data Index: 802200 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7095. Min Act: -0.0001

Data Index: 53826 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6791. Min Act: -0.0001

Data Index: 775056 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7123. Min Act: -0.0001

Data Index: 867552 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7040. Min Act: -0.0002

Data Index: 257676 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7193. Min Act: -0.0002

Data Index: 1295708 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6198. Min Act: -0.0002

Data Index: 851875 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6795. Min Act: -0.0001

Data Index: 1185274 (C4 (Web Text))

Max Activating Token Index: 334