Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4186 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.2054. Min Act: -0.0000

Data Index: 310347 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.1578. Min Act: -0.0000

Data Index: 769098 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.2230. Min Act: -0.0000

Data Index: 484637 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.1298. Min Act: -0.0000

Data Index: 1189939 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.2146. Min Act: -0.0000

Data Index: 1232439 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1116868 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.1264. Min Act: -0.0000

Data Index: 770346 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.0307. Min Act: -0.0000

Data Index: 80042 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.0333. Min Act: -0.0000

Data Index: 336573 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.0496. Min Act: -0.0000

Data Index: 187481 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.0327. Min Act: -0.0000

Data Index: 300415 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9747. Min Act: -0.0000

Data Index: 788962 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9956. Min Act: -0.0000

Data Index: 649140 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9066. Min Act: -0.0000

Data Index: 865131 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1163413 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9902. Min Act: -0.0000

Data Index: 630264 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9252. Min Act: -0.0000

Data Index: 412963 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9838. Min Act: -0.0000

Data Index: 1431593 (Python Code)

Max Activating Token Index: 255

Text #18

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.8246. Min Act: -0.0000

Data Index: 307264 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1059459 (C4 (Web Text))

Max Activating Token Index: 374