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

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

Neuron 2857 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3159. Min Range: -1.3159

Max Act: 1.3159. Min Act: -0.0001

Data Index: 1632748 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 1.3159. Min Range: -1.3159

Max Act: 1.2268. Min Act: -0.0001

Data Index: 422776 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 1.3159. Min Range: -1.3159

Max Act: 1.1167. Min Act: -0.0001

Data Index: 771772 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.3159. Min Range: -1.3159

Max Act: 1.0744. Min Act: -0.0001

Data Index: 1452148 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.9693. Min Act: -0.0001

Data Index: 329679 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.3159. Min Range: -1.3159

Max Act: 1.0811. Min Act: -0.0001

Data Index: 1135491 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 1.3159. Min Range: -1.3159

Max Act: 1.0261. Min Act: -0.0001

Data Index: 954476 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.9122. Min Act: -0.0001

Data Index: 763912 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 1.3159. Min Range: -1.3159

Max Act: 1.0791. Min Act: -0.0001

Data Index: 1614034 (Python Code)

Max Activating Token Index: 993

Text #9

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.9755. Min Act: -0.0001

Data Index: 520507 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.9871. Min Act: -0.0001

Data Index: 786122 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.9763. Min Act: -0.0001

Data Index: 272332 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 1.3159. Min Range: -1.3159

Max Act: 1.0232. Min Act: -0.0001

Data Index: 66253 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.9604. Min Act: -0.0001

Data Index: 1372551 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.9237. Min Act: -0.0001

Data Index: 930247 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.9510. Min Act: -0.0001

Data Index: 859471 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.8708. Min Act: -0.0001

Data Index: 781055 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.9741. Min Act: -0.0001

Data Index: 1005786 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.8386. Min Act: -0.0001

Data Index: 470568 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.3159. Min Range: -1.3159

Max Act: 0.8847. Min Act: -0.0001

Data Index: 718987 (C4 (Web Text))

Max Activating Token Index: 428