Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2099 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1127. Min Range: -1.1127

Max Act: 1.0933. Min Act: -0.0001

Data Index: 1537122 (Python Code)

Max Activating Token Index: 511

Text #1

Max Range: 1.1127. Min Range: -1.1127

Max Act: 1.1127. Min Act: -0.0001

Data Index: 1382618 (Python Code)

Max Activating Token Index: 802

Text #2

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.9216. Min Act: -0.0001

Data Index: 1437970 (Python Code)

Max Activating Token Index: 388

Text #3

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8624. Min Act: -0.0001

Data Index: 1412238 (Python Code)

Max Activating Token Index: 609

Text #4

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8981. Min Act: -0.0001

Data Index: 1444323 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8658. Min Act: -0.0001

Data Index: 1364251 (Python Code)

Max Activating Token Index: 533

Text #6

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8237. Min Act: -0.0001

Data Index: 1403500 (Python Code)

Max Activating Token Index: 711

Text #7

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7859. Min Act: -0.0001

Data Index: 1515815 (Python Code)

Max Activating Token Index: 962

Text #8

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7536. Min Act: -0.0001

Data Index: 1580777 (Python Code)

Max Activating Token Index: 954

Text #9

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7966. Min Act: -0.0001

Data Index: 1372076 (Python Code)

Max Activating Token Index: 911

Text #10

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7459. Min Act: -0.0001

Data Index: 1530618 (Python Code)

Max Activating Token Index: 689

Text #11

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7643. Min Act: -0.0001

Data Index: 1529665 (Python Code)

Max Activating Token Index: 586

Text #12

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.6963. Min Act: -0.0001

Data Index: 1595599 (Python Code)

Max Activating Token Index: 630

Text #13

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7822. Min Act: -0.0001

Data Index: 1404194 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7246. Min Act: -0.0001

Data Index: 1550217 (Python Code)

Max Activating Token Index: 924

Text #15

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7735. Min Act: -0.0001

Data Index: 1426367 (Python Code)

Max Activating Token Index: 398

Text #16

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7701. Min Act: -0.0001

Data Index: 1452855 (Python Code)

Max Activating Token Index: 336

Text #17

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7381. Min Act: -0.0001

Data Index: 1543657 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.6952. Min Act: -0.0001

Data Index: 1493222 (Python Code)

Max Activating Token Index: 129

Text #19

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.6747. Min Act: -0.0001

Data Index: 1641270 (Python Code)

Max Activating Token Index: 724