Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1373 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0187. Min Range: -1.0187

Max Act: 1.0187. Min Act: -0.0000

Data Index: 735084 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1029322 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8849. Min Act: -0.0000

Data Index: 501101 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8150. Min Act: -0.0000

Data Index: 118542 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8493. Min Act: -0.0001

Data Index: 900892 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8114. Min Act: -0.0000

Data Index: 916108 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7881. Min Act: -0.0000

Data Index: 350700 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7715. Min Act: -0.0000

Data Index: 19678 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7848. Min Act: -0.0000

Data Index: 481961 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7969. Min Act: -0.0000

Data Index: 739778 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7386. Min Act: -0.0000

Data Index: 46880 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7597. Min Act: -0.0000

Data Index: 984118 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7647. Min Act: -0.0000

Data Index: 254469 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7423. Min Act: -0.0000

Data Index: 156980 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7855. Min Act: -0.0000

Data Index: 895187 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1282857 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7945. Min Act: -0.0001

Data Index: 693557 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7149. Min Act: -0.0000

Data Index: 263239 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7141. Min Act: -0.0000

Data Index: 429006 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.7326. Min Act: -0.0000

Data Index: 63000 (C4 (Web Text))

Max Activating Token Index: 433