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

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

Neuron 896 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.6041. Min Act: -0.0000

Data Index: 70989 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.5282. Min Act: -0.0000

Data Index: 154825 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.3001. Min Act: -0.0000

Data Index: 476882 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.4018. Min Act: -0.0000

Data Index: 145242 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.0722. Min Act: -0.0000

Data Index: 1183988 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.1694. Min Act: -0.0000

Data Index: 995947 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.9005. Min Act: -0.0000

Data Index: 434533 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.0026. Min Act: -0.0001

Data Index: 569077 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.0026. Min Act: -0.0000

Data Index: 246640 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.0992. Min Act: -0.0000

Data Index: 1195862 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.7715. Min Act: -0.0001

Data Index: 1260109 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.0159. Min Act: -0.0000

Data Index: 290497 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.0217. Min Act: -0.0001

Data Index: 725648 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.1551. Min Act: -0.0000

Data Index: 621449 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.8298. Min Act: -0.0000

Data Index: 783725 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.5925. Min Act: -0.0001

Data Index: 1053567 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.6957. Min Act: -0.0001

Data Index: 463547 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.4113. Min Act: -0.0000

Data Index: 889556 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.5783. Min Act: -0.0001

Data Index: 310296 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.5431. Min Act: -0.0000

Data Index: 210904 (C4 (Web Text))

Max Activating Token Index: 232