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

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

Neuron 2842 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.6710. Min Act: -0.0001

Data Index: 1432943 (Python Code)

Max Activating Token Index: 985

Text #1

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.6854. Min Act: -0.0001

Data Index: 1395431 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5498. Min Act: -0.0001

Data Index: 511600 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5323. Min Act: -0.0001

Data Index: 48455 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5231. Min Act: -0.0001

Data Index: 706157 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5075. Min Act: -0.0001

Data Index: 1054812 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5193. Min Act: -0.0001

Data Index: 218983 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5019. Min Act: -0.0001

Data Index: 1177311 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5126. Min Act: -0.0001

Data Index: 1206496 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4645. Min Act: -0.0001

Data Index: 774730 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4935. Min Act: -0.0001

Data Index: 612916 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4736. Min Act: -0.0001

Data Index: 189274 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4753. Min Act: -0.0001

Data Index: 1316196 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4731. Min Act: -0.0001

Data Index: 979662 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4659. Min Act: -0.0001

Data Index: 695927 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4559. Min Act: -0.0001

Data Index: 1216845 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4399. Min Act: -0.0001

Data Index: 1185550 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4682. Min Act: -0.0001

Data Index: 1243522 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4687. Min Act: -0.0001

Data Index: 553552 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4333. Min Act: -0.0001

Data Index: 1446522 (Python Code)

Max Activating Token Index: 379