Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 636 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1971. Min Act: -0.0001

Data Index: 467119 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1855. Min Act: -0.0001

Data Index: 882420 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1776. Min Act: -0.0001

Data Index: 317226 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1461. Min Act: -0.0001

Data Index: 443232 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1711. Min Act: -0.0001

Data Index: 1039381 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1248693 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1346794 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1543. Min Act: -0.0001

Data Index: 30905 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1429. Min Act: -0.0001

Data Index: 924600 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1091071 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1083. Min Act: -0.0001

Data Index: 324280 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1091. Min Act: -0.0001

Data Index: 223283 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1078. Min Act: -0.0001

Data Index: 378970 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1018. Min Act: -0.0001

Data Index: 379806 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1136391 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0880. Min Act: -0.0001

Data Index: 426252 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1271323 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0868. Min Act: -0.0001

Data Index: 984923 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0919. Min Act: -0.0001

Data Index: 953795 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0922. Min Act: -0.0001

Data Index: 250299 (C4 (Web Text))

Max Activating Token Index: 172