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

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

Neuron 5092 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5082. Min Range: -1.5082

Max Act: 1.5082. Min Act: -0.0000

Data Index: 783186 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1151858 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.8996. Min Act: -0.0000

Data Index: 1332279 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.8162. Min Act: -0.0000

Data Index: 158024 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.8666. Min Act: -0.0000

Data Index: 373169 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.7847. Min Act: -0.0000

Data Index: 696561 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.7724. Min Act: -0.0000

Data Index: 593335 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1504823 (Python Code)

Max Activating Token Index: 220

Text #8

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.7214. Min Act: -0.0000

Data Index: 528003 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.7287. Min Act: -0.0000

Data Index: 416891 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1437704 (Python Code)

Max Activating Token Index: 833

Text #11

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1384632 (Python Code)

Max Activating Token Index: 412

Text #12

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1033947 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.7186. Min Act: -0.0000

Data Index: 674557 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1531571 (Python Code)

Max Activating Token Index: 407

Text #15

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.7570. Min Act: -0.0000

Data Index: 316841 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.6373. Min Act: -0.0000

Data Index: 475997 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1325662 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.6471. Min Act: -0.0000

Data Index: 853873 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.5082. Min Range: -1.5082

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1549632 (Python Code)

Max Activating Token Index: 512