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

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

Neuron 1743 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.7726. Min Act: -0.0002

Data Index: 1587169 (Python Code)

Max Activating Token Index: 655

Text #1

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.6672. Min Act: -0.0002

Data Index: 1488565 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.6898. Min Act: -0.0002

Data Index: 1655724 (Python Code)

Max Activating Token Index: 134

Text #3

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.6234. Min Act: -0.0002

Data Index: 1414095 (Python Code)

Max Activating Token Index: 367

Text #4

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5921. Min Act: -0.0002

Data Index: 1327683 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5761. Min Act: -0.0002

Data Index: 1077107 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5515. Min Act: -0.0002

Data Index: 146439 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5273. Min Act: -0.0002

Data Index: 795548 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5220. Min Act: -0.0002

Data Index: 1477160 (Python Code)

Max Activating Token Index: 556

Text #9

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5370. Min Act: -0.0002

Data Index: 171260 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5367. Min Act: -0.0002

Data Index: 23552 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5316. Min Act: -0.0002

Data Index: 1553979 (Python Code)

Max Activating Token Index: 402

Text #12

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5009. Min Act: -0.0002

Data Index: 104204 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5017. Min Act: -0.0002

Data Index: 1386621 (Python Code)

Max Activating Token Index: 500

Text #14

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5136. Min Act: -0.0002

Data Index: 1425788 (Python Code)

Max Activating Token Index: 715

Text #15

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.4847. Min Act: -0.0002

Data Index: 1510593 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.5165. Min Act: -0.0002

Data Index: 1515177 (Python Code)

Max Activating Token Index: 358

Text #17

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.4990. Min Act: -0.0002

Data Index: 1311886 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.4951. Min Act: -0.0002

Data Index: 107246 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.7726. Min Range: -0.7726

Max Act: 0.4887. Min Act: -0.0002

Data Index: 1655477 (Python Code)

Max Activating Token Index: 135