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

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

Neuron 3522 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.1670. Min Act: -0.0001

Data Index: 1397581 (Python Code)

Max Activating Token Index: 198

Text #1

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.1514. Min Act: -0.0001

Data Index: 1569404 (Python Code)

Max Activating Token Index: 164

Text #2

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0873. Min Act: -0.0001

Data Index: 458322 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9466. Min Act: -0.0001

Data Index: 1361018 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0009. Min Act: -0.0001

Data Index: 125572 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9722. Min Act: -0.0001

Data Index: 1524374 (Python Code)

Max Activating Token Index: 110

Text #6

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9903. Min Act: -0.0001

Data Index: 1512961 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9903. Min Act: -0.0001

Data Index: 347384 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0159. Min Act: -0.0001

Data Index: 773066 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9597. Min Act: -0.0001

Data Index: 33479 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9720. Min Act: -0.0001

Data Index: 749988 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9511. Min Act: -0.0001

Data Index: 1090818 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9158. Min Act: -0.0001

Data Index: 1296105 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9080. Min Act: -0.0001

Data Index: 543606 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9064. Min Act: -0.0001

Data Index: 345760 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.7924. Min Act: -0.0001

Data Index: 344070 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9459. Min Act: -0.0001

Data Index: 1284051 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.8924. Min Act: -0.0001

Data Index: 954259 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.8101. Min Act: -0.0001

Data Index: 216361 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.8655. Min Act: -0.0001

Data Index: 1402974 (Python Code)

Max Activating Token Index: 39