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

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

Neuron 1915 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.2531. Min Act: -0.0001

Data Index: 952511 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.1884. Min Act: -0.0001

Data Index: 51118 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.1439. Min Act: -0.0001

Data Index: 866444 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0659. Min Act: -0.0001

Data Index: 69515 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0800. Min Act: -0.0001

Data Index: 1336013 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0453. Min Act: -0.0001

Data Index: 826967 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0015. Min Act: -0.0001

Data Index: 753293 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9411. Min Act: -0.0001

Data Index: 349165 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0321. Min Act: -0.0001

Data Index: 354546 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0096. Min Act: -0.0001

Data Index: 1219200 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9392. Min Act: -0.0001

Data Index: 1190772 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.8934. Min Act: -0.0001

Data Index: 433343 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9842. Min Act: -0.0001

Data Index: 634364 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.8892. Min Act: -0.0001

Data Index: 1069455 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9124. Min Act: -0.0001

Data Index: 52882 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.8590. Min Act: -0.0001

Data Index: 35306 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.8439. Min Act: -0.0001

Data Index: 31197 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.8303. Min Act: -0.0001

Data Index: 727365 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9312. Min Act: -0.0001

Data Index: 213288 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.8396. Min Act: -0.0001

Data Index: 550150 (C4 (Web Text))

Max Activating Token Index: 435