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

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

Neuron 312 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.6336. Min Act: -0.0001

Data Index: 69686 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.6212. Min Act: -0.0001

Data Index: 548406 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5452. Min Act: -0.0001

Data Index: 1304863 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5759. Min Act: -0.0001

Data Index: 856875 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5138. Min Act: -0.0001

Data Index: 1149374 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5174. Min Act: -0.0001

Data Index: 337415 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5859. Min Act: -0.0001

Data Index: 241979 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5344. Min Act: -0.0001

Data Index: 678212 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4810. Min Act: -0.0001

Data Index: 1006659 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4995. Min Act: -0.0001

Data Index: 1059230 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4798. Min Act: -0.0001

Data Index: 633991 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4605. Min Act: -0.0001

Data Index: 1219200 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4709. Min Act: -0.0001

Data Index: 1306577 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4493. Min Act: -0.0001

Data Index: 545655 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5253. Min Act: -0.0001

Data Index: 887412 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4432. Min Act: -0.0001

Data Index: 1087643 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4080. Min Act: -0.0001

Data Index: 938495 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4508. Min Act: -0.0001

Data Index: 323520 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4369. Min Act: -0.0001

Data Index: 288185 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4697. Min Act: -0.0001

Data Index: 254990 (C4 (Web Text))

Max Activating Token Index: 689