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

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

Neuron 4122 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: 1.1067. Min Range: -1.1067

Max Act: 0.9971. Min Act: -0.0001

Data Index: 152561 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 1.1067. Min Range: -1.1067

Max Act: 1.1067. Min Act: -0.0001

Data Index: 852768 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 1.1067. Min Range: -1.1067

Max Act: 1.0636. Min Act: -0.0001

Data Index: 1269484 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.8957. Min Act: -0.0001

Data Index: 499224 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9339. Min Act: -0.0001

Data Index: 820203 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.1067. Min Range: -1.1067

Max Act: 1.0268. Min Act: -0.0001

Data Index: 1048811 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.8625. Min Act: -0.0001

Data Index: 124003 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9009. Min Act: -0.0001

Data Index: 832295 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.8579. Min Act: -0.0001

Data Index: 1092878 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9332. Min Act: -0.0001

Data Index: 306331 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.8169. Min Act: -0.0001

Data Index: 1249486 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9327. Min Act: -0.0001

Data Index: 1113352 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.8305. Min Act: -0.0001

Data Index: 19259 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.8609. Min Act: -0.0001

Data Index: 1337238 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.8513. Min Act: -0.0001

Data Index: 376187 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.7775. Min Act: -0.0001

Data Index: 1247927 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.7758. Min Act: -0.0001

Data Index: 157395 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.7622. Min Act: -0.0000

Data Index: 1164671 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.8348. Min Act: -0.0001

Data Index: 1079329 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.8424. Min Act: -0.0001

Data Index: 314432 (C4 (Web Text))

Max Activating Token Index: 674