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

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

Neuron 1867 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.4490. Min Act: -0.0003

Data Index: 800993 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.4606. Min Act: -0.0003

Data Index: 413351 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3599. Min Act: -0.0003

Data Index: 221222 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3710. Min Act: -0.0003

Data Index: 777161 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3761. Min Act: -0.0003

Data Index: 491802 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3780. Min Act: -0.0003

Data Index: 330318 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3132. Min Act: -0.0003

Data Index: 262113 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.4237. Min Act: -0.0003

Data Index: 63228 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3492. Min Act: -0.0003

Data Index: 324060 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3360. Min Act: -0.0003

Data Index: 1307535 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3505. Min Act: -0.0003

Data Index: 372637 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3733. Min Act: -0.0003

Data Index: 921680 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3588. Min Act: -0.0003

Data Index: 1079475 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3321. Min Act: -0.0003

Data Index: 974196 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3946. Min Act: -0.0003

Data Index: 319463 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3989. Min Act: -0.0003

Data Index: 240878 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3146. Min Act: -0.0003

Data Index: 922221 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3324. Min Act: -0.0003

Data Index: 429486 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3841. Min Act: -0.0003

Data Index: 797564 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3600. Min Act: -0.0003

Data Index: 25163 (C4 (Web Text))

Max Activating Token Index: 487