Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1583 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.5909. Min Act: -0.0003

Data Index: 557467 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.5412. Min Act: -0.0003

Data Index: 1241571 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.5421. Min Act: -0.0003

Data Index: 357227 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4652. Min Act: -0.0003

Data Index: 916832 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4644. Min Act: -0.0003

Data Index: 474110 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4576. Min Act: -0.0003

Data Index: 1000814 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4207. Min Act: -0.0003

Data Index: 1188740 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4479. Min Act: -0.0003

Data Index: 46367 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4467. Min Act: -0.0003

Data Index: 667400 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4372. Min Act: -0.0003

Data Index: 1039021 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4605. Min Act: -0.0003

Data Index: 449799 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4311. Min Act: -0.0003

Data Index: 263049 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4259. Min Act: -0.0003

Data Index: 49968 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4246. Min Act: -0.0004

Data Index: 130873 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4514. Min Act: -0.0003

Data Index: 1055007 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4179. Min Act: -0.0003

Data Index: 297533 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4124. Min Act: -0.0003

Data Index: 1157026 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.3840. Min Act: -0.0003

Data Index: 1148453 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.3823. Min Act: -0.0003

Data Index: 882745 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.5909. Min Range: -0.5909

Max Act: 0.4089. Min Act: -0.0003

Data Index: 1163478 (C4 (Web Text))

Max Activating Token Index: 815