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

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

Neuron 2469 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.9607. Min Act: -0.0000

Data Index: 1067272 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.8368. Min Act: -0.0000

Data Index: 780491 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.5839. Min Act: -0.0000

Data Index: 783553 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.6152. Min Act: -0.0000

Data Index: 1268273 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.4339. Min Act: -0.0000

Data Index: 1010955 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.4597. Min Act: -0.0001

Data Index: 298345 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1221214 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.5332. Min Act: -0.0000

Data Index: 22010 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.4255. Min Act: -0.0000

Data Index: 294628 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.3882. Min Act: -0.0000

Data Index: 970034 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.3738. Min Act: -0.0000

Data Index: 770259 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.3744. Min Act: -0.0000

Data Index: 862753 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.3613. Min Act: -0.0000

Data Index: 788494 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.3942. Min Act: -0.0000

Data Index: 790257 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.3437. Min Act: -0.0000

Data Index: 53258 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.3223. Min Act: -0.0000

Data Index: 673531 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.3617. Min Act: -0.0000

Data Index: 697334 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.3216. Min Act: -0.0000

Data Index: 200214 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.2976. Min Act: -0.0000

Data Index: 406945 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.9607. Min Range: -1.9607

Max Act: 1.1868. Min Act: -0.0000

Data Index: 1255303 (C4 (Web Text))

Max Activating Token Index: 993