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

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

Neuron 407 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1202013 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.8083. Min Act: 0.0000

Data Index: 393946 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7931. Min Act: 0.0002

Data Index: 89726 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7511. Min Act: 0.0000

Data Index: 943107 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1281051 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1015063 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6382. Min Act: 0.0001

Data Index: 1296274 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6023. Min Act: -0.0000

Data Index: 939086 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6230. Min Act: -0.0000

Data Index: 939130 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1014156 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6144. Min Act: 0.0002

Data Index: 101128 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1233145 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5644. Min Act: 0.0000

Data Index: 764507 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5699. Min Act: -0.0000

Data Index: 68189 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1177507 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5591. Min Act: -0.0000

Data Index: 244619 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1210057 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5593. Min Act: -0.0000

Data Index: 694837 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5209. Min Act: -0.0000

Data Index: 605725 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5123. Min Act: 0.0000

Data Index: 1227902 (C4 (Web Text))

Max Activating Token Index: 566