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

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

Neuron 3217 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: 0.5124. Min Range: -0.5124

Max Act: 0.5124. Min Act: -0.0000

Data Index: 875650 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.5074. Min Act: -0.0000

Data Index: 635655 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4667. Min Act: -0.0000

Data Index: 12609 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4654. Min Act: -0.0000

Data Index: 684209 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4295. Min Act: -0.0000

Data Index: 577346 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4724. Min Act: -0.0000

Data Index: 230797 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4545. Min Act: -0.0000

Data Index: 537522 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4353. Min Act: -0.0000

Data Index: 405120 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4347. Min Act: -0.0000

Data Index: 570778 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4303. Min Act: -0.0000

Data Index: 10055 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4253. Min Act: -0.0001

Data Index: 1022409 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4534. Min Act: -0.0000

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4490. Min Act: -0.0000

Data Index: 678959 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4300. Min Act: -0.0000

Data Index: 60054 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1002693 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4262. Min Act: -0.0000

Data Index: 304881 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1310606 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1161740 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1286248 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.5124. Min Range: -0.5124

Max Act: 0.4045. Min Act: -0.0000

Data Index: 513412 (C4 (Web Text))

Max Activating Token Index: 605