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

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

Neuron 1024 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1900. Min Range: -2.1900

Max Act: 2.1900. Min Act: -0.0000

Data Index: 276420 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.4940. Min Act: -0.0000

Data Index: 1354729 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1172463 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.3721. Min Act: -0.0000

Data Index: 1268478 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.2849. Min Act: -0.0000

Data Index: 693857 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.3468. Min Act: -0.0000

Data Index: 754027 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.2910. Min Act: -0.0000

Data Index: 69090 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.2422. Min Act: -0.0000

Data Index: 1094488 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.3553. Min Act: -0.0000

Data Index: 967805 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1137195 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.0877. Min Act: -0.0000

Data Index: 546541 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.0259. Min Act: -0.0000

Data Index: 624809 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.2104. Min Act: -0.0000

Data Index: 843711 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.2326. Min Act: -0.0000

Data Index: 1092236 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.1966. Min Act: -0.0000

Data Index: 238994 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.1158. Min Act: -0.0000

Data Index: 548169 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1281411 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1353523 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.2386. Min Act: -0.0000

Data Index: 854595 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 2.1900. Min Range: -2.1900

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1322996 (C4 (Web Text))

Max Activating Token Index: 611