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

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

Neuron 1934 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.6347. Min Act: -0.0003

Data Index: 501457 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4582. Min Act: -0.0003

Data Index: 420349 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.1275. Min Act: -0.0003

Data Index: 1179779 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.7668. Min Act: -0.0003

Data Index: 12440 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.5775. Min Act: -0.0003

Data Index: 1346462 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.7798. Min Act: -0.0003

Data Index: 386669 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.7657. Min Act: -0.0003

Data Index: 1271264 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.7665. Min Act: -0.0003

Data Index: 1346733 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.7512. Min Act: -0.0003

Data Index: 925828 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.6342. Min Act: -0.0003

Data Index: 661324 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.6765. Min Act: -0.0004

Data Index: 643579 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.4400. Min Act: -0.0003

Data Index: 560192 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.5975. Min Act: -0.0003

Data Index: 259878 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.7388. Min Act: -0.0003

Data Index: 1037116 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.3254. Min Act: -0.0003

Data Index: 762916 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.7729. Min Act: -0.0003

Data Index: 870169 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.4976. Min Act: -0.0003

Data Index: 743007 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.5763. Min Act: -0.0003

Data Index: 703608 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.5058. Min Act: -0.0003

Data Index: 1036492 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 3.6347. Min Range: -3.6347

Max Act: 2.4307. Min Act: -0.0003

Data Index: 341702 (C4 (Web Text))

Max Activating Token Index: 392