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

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

Neuron 2929 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0067. Min Range: -1.0067

Max Act: 1.0067. Min Act: -0.0001

Data Index: 816449 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9647. Min Act: -0.0001

Data Index: 362928 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9107. Min Act: -0.0001

Data Index: 715092 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8877. Min Act: -0.0001

Data Index: 1310073 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8440. Min Act: -0.0001

Data Index: 71452 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8400. Min Act: -0.0001

Data Index: 1131906 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8578. Min Act: -0.0001

Data Index: 1294874 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8470. Min Act: -0.0001

Data Index: 868127 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8041. Min Act: -0.0001

Data Index: 377164 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8256. Min Act: -0.0001

Data Index: 981724 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8225. Min Act: -0.0001

Data Index: 691600 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8150. Min Act: -0.0001

Data Index: 234915 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8440. Min Act: -0.0001

Data Index: 1353955 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7782. Min Act: -0.0001

Data Index: 347948 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7788. Min Act: -0.0001

Data Index: 331027 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8062. Min Act: -0.0001

Data Index: 249421 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8031. Min Act: -0.0001

Data Index: 591460 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8244. Min Act: -0.0001

Data Index: 555659 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7456. Min Act: -0.0001

Data Index: 1142380 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7920. Min Act: -0.0001

Data Index: 810366 (C4 (Web Text))

Max Activating Token Index: 703