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

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

Neuron 2714 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.4394. Min Act: -0.0001

Data Index: 1080459 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.3857. Min Act: -0.0001

Data Index: 1279408 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.2757. Min Act: -0.0001

Data Index: 31240 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.2857. Min Act: -0.0001

Data Index: 1026966 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.0654. Min Act: -0.0001

Data Index: 15173 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.1581. Min Act: -0.0001

Data Index: 219386 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.0706. Min Act: -0.0001

Data Index: 1029174 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.0719. Min Act: -0.0001

Data Index: 204105 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.1190. Min Act: -0.0001

Data Index: 57495 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.1920. Min Act: -0.0001

Data Index: 375835 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.1568. Min Act: -0.0001

Data Index: 3745 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.0983. Min Act: -0.0001

Data Index: 445616 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.1236. Min Act: -0.0001

Data Index: 1221855 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.0224. Min Act: -0.0001

Data Index: 859831 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.4394. Min Range: -1.4394

Max Act: 0.9780. Min Act: -0.0001

Data Index: 211221 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.0560. Min Act: -0.0001

Data Index: 468696 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 1.4394. Min Range: -1.4394

Max Act: 0.9813. Min Act: -0.0001

Data Index: 670679 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.0421. Min Act: -0.0001

Data Index: 642402 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.0381. Min Act: -0.0001

Data Index: 721915 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 1.4394. Min Range: -1.4394

Max Act: 1.0429. Min Act: -0.0001

Data Index: 1121827 (C4 (Web Text))

Max Activating Token Index: 621