Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5335 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3678. Min Range: -2.3678

Max Act: 2.3678. Min Act: -0.0000

Data Index: 921103 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 2.3678. Min Range: -2.3678

Max Act: 2.2337. Min Act: -0.0000

Data Index: 772211 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 2.3678. Min Range: -2.3678

Max Act: 2.3274. Min Act: -0.0000

Data Index: 1315218 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 2.3678. Min Range: -2.3678

Max Act: 2.2838. Min Act: -0.0000

Data Index: 934027 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 2.3678. Min Range: -2.3678

Max Act: 2.0532. Min Act: -0.0000

Data Index: 660254 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 2.3678. Min Range: -2.3678

Max Act: 2.0180. Min Act: -0.0000

Data Index: 109171 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 2.3678. Min Range: -2.3678

Max Act: 2.0989. Min Act: -0.0000

Data Index: 313936 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 2.3678. Min Range: -2.3678

Max Act: 2.0952. Min Act: -0.0000

Data Index: 772235 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 2.3678. Min Range: -2.3678

Max Act: 1.9368. Min Act: -0.0000

Data Index: 1301660 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 2.3678. Min Range: -2.3678

Max Act: 2.0350. Min Act: -0.0000

Data Index: 147928 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 2.3678. Min Range: -2.3678

Max Act: 1.9042. Min Act: -0.0000

Data Index: 1027603 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 2.3678. Min Range: -2.3678

Max Act: 1.9829. Min Act: -0.0000

Data Index: 276943 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 2.3678. Min Range: -2.3678

Max Act: 1.9470. Min Act: -0.0000

Data Index: 456774 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 2.3678. Min Range: -2.3678

Max Act: 1.9302. Min Act: -0.0000

Data Index: 380428 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 2.3678. Min Range: -2.3678

Max Act: 1.8181. Min Act: -0.0000

Data Index: 541142 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 2.3678. Min Range: -2.3678

Max Act: 2.0077. Min Act: -0.0000

Data Index: 993660 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 2.3678. Min Range: -2.3678

Max Act: 1.8708. Min Act: -0.0000

Data Index: 1067836 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 2.3678. Min Range: -2.3678

Max Act: 1.8401. Min Act: -0.0000

Data Index: 1099231 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 2.3678. Min Range: -2.3678

Max Act: 1.7259. Min Act: -0.0000

Data Index: 650203 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 2.3678. Min Range: -2.3678

Max Act: 1.8113. Min Act: -0.0000

Data Index: 339693 (C4 (Web Text))

Max Activating Token Index: 609