Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1333 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.1079. Min Act: 0.0000

Data Index: 1154299 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.1898. Min Act: 0.0000

Data Index: 611179 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.0860. Min Act: -0.0000

Data Index: 891068 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.0676. Min Act: -0.0000

Data Index: 389581 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.0529. Min Act: 0.0000

Data Index: 583515 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.0169. Min Act: -0.0000

Data Index: 452367 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9561. Min Act: 0.0000

Data Index: 864126 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.0621. Min Act: -0.0000

Data Index: 379350 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9584. Min Act: -0.0000

Data Index: 792700 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9409. Min Act: -0.0000

Data Index: 427828 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8980. Min Act: 0.0000

Data Index: 1304371 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1091003 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8580. Min Act: -0.0000

Data Index: 389473 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8330. Min Act: -0.0000

Data Index: 526979 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8029. Min Act: 0.0000

Data Index: 501325 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8061. Min Act: 0.0000

Data Index: 1132168 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8271. Min Act: -0.0000

Data Index: 486845 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.7942. Min Act: 0.0000

Data Index: 573122 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8629. Min Act: 0.0000

Data Index: 1159700 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.7871. Min Act: -0.0000

Data Index: 495094 (C4 (Web Text))

Max Activating Token Index: 607