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

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

Neuron 605 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3262. Min Act: -0.0001

Data Index: 870068 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1061698 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3185. Min Act: -0.0001

Data Index: 642054 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2866. Min Act: -0.0001

Data Index: 505322 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3064. Min Act: -0.0001

Data Index: 374676 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3044. Min Act: -0.0001

Data Index: 229162 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2912. Min Act: -0.0001

Data Index: 601670 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3068. Min Act: -0.0001

Data Index: 1323749 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2945. Min Act: -0.0001

Data Index: 679745 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2896. Min Act: -0.0001

Data Index: 1349108 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2887. Min Act: -0.0001

Data Index: 343539 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3071. Min Act: -0.0001

Data Index: 77293 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2763. Min Act: -0.0001

Data Index: 129820 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2830. Min Act: -0.0001

Data Index: 213141 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2374. Min Act: -0.0001

Data Index: 511036 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2780. Min Act: -0.0001

Data Index: 1323427 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2813. Min Act: -0.0001

Data Index: 39520 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2668. Min Act: -0.0001

Data Index: 741565 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2730. Min Act: -0.0001

Data Index: 244923 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2743. Min Act: -0.0001

Data Index: 971032 (C4 (Web Text))

Max Activating Token Index: 39