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

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

Neuron 3191 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: 2.2411. Min Range: -2.2411

Max Act: 2.2411. Min Act: -0.0000

Data Index: 959928 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.8307. Min Act: -0.0000

Data Index: 680255 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.8201. Min Act: -0.0000

Data Index: 1315010 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.8073. Min Act: -0.0000

Data Index: 614742 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.7535. Min Act: -0.0000

Data Index: 1195319 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.7415. Min Act: -0.0000

Data Index: 878509 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.7098. Min Act: -0.0000

Data Index: 1281524 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.6953. Min Act: -0.0000

Data Index: 1047841 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.6506. Min Act: -0.0000

Data Index: 479914 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.6497. Min Act: -0.0000

Data Index: 31596 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.7080. Min Act: -0.0000

Data Index: 190624 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.5934. Min Act: -0.0000

Data Index: 7372 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.5781. Min Act: -0.0000

Data Index: 255541 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.5647. Min Act: -0.0000

Data Index: 1079450 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.5269. Min Act: -0.0000

Data Index: 1347580 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.5152. Min Act: -0.0000

Data Index: 1338029 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.5251. Min Act: -0.0000

Data Index: 213115 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.4402. Min Act: -0.0000

Data Index: 730030 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1344508 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 2.2411. Min Range: -2.2411

Max Act: 1.5042. Min Act: -0.0000

Data Index: 393948 (C4 (Web Text))

Max Activating Token Index: 873