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

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

Neuron 4948 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2744. Min Range: -1.2744

Max Act: 1.2527. Min Act: -0.0000

Data Index: 832665 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 1.2744. Min Range: -1.2744

Max Act: 1.2744. Min Act: 0.0000

Data Index: 510318 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 1.2744. Min Range: -1.2744

Max Act: 1.1569. Min Act: -0.0000

Data Index: 813517 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 1.2744. Min Range: -1.2744

Max Act: 1.0816. Min Act: -0.0000

Data Index: 1261263 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 1.2744. Min Range: -1.2744

Max Act: 1.0889. Min Act: -0.0000

Data Index: 793935 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.9567. Min Act: -0.0000

Data Index: 703569 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 1.2744. Min Range: -1.2744

Max Act: 1.0138. Min Act: -0.0000

Data Index: 909197 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1302783 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.9059. Min Act: -0.0000

Data Index: 315719 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7873. Min Act: -0.0000

Data Index: 647790 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8211. Min Act: -0.0000

Data Index: 373197 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8149. Min Act: -0.0000

Data Index: 400598 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.6995. Min Act: -0.0000

Data Index: 781582 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7098. Min Act: -0.0000

Data Index: 899558 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1008515 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.6708. Min Act: -0.0000

Data Index: 322764 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8790. Min Act: 0.0000

Data Index: 428912 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7821. Min Act: 0.0001

Data Index: 630058 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1011831 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7564. Min Act: -0.0000

Data Index: 999347 (C4 (Web Text))

Max Activating Token Index: 300