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

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

Neuron 355 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: 1.8213. Min Range: -1.8213

Max Act: 1.7682. Min Act: -0.0003

Data Index: 568470 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.5801. Min Act: -0.0003

Data Index: 422250 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.8213. Min Act: -0.0003

Data Index: 286307 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.6368. Min Act: -0.0003

Data Index: 70102 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.7070. Min Act: -0.0003

Data Index: 882282 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.2709. Min Act: -0.0003

Data Index: 71851 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.6811. Min Act: -0.0003

Data Index: 552492 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.6704. Min Act: -0.0003

Data Index: 185783 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.4491. Min Act: -0.0003

Data Index: 836600 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.7871. Min Act: -0.0003

Data Index: 1274072 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.4290. Min Act: -0.0003

Data Index: 1295882 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.5512. Min Act: -0.0003

Data Index: 1176062 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.5101. Min Act: -0.0003

Data Index: 267477 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.2988. Min Act: -0.0003

Data Index: 515194 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.6353. Min Act: -0.0003

Data Index: 1303600 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.3499. Min Act: -0.0003

Data Index: 1076373 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.3960. Min Act: -0.0003

Data Index: 790214 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.3068. Min Act: -0.0003

Data Index: 1231182 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.5037. Min Act: -0.0003

Data Index: 720793 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.4649. Min Act: -0.0003

Data Index: 501901 (C4 (Web Text))

Max Activating Token Index: 424