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

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

Neuron 3220 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4995. Min Range: -4.4995

Max Act: 4.4922. Min Act: -0.0000

Data Index: 211966 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 4.4995. Min Range: -4.4995

Max Act: 4.4995. Min Act: -0.0000

Data Index: 1302676 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 4.4995. Min Range: -4.4995

Max Act: 4.2790. Min Act: -0.0000

Data Index: 984333 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 4.4995. Min Range: -4.4995

Max Act: 4.0163. Min Act: -0.0000

Data Index: 577513 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 4.4995. Min Range: -4.4995

Max Act: 4.0002. Min Act: 0.0000

Data Index: 166376 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.9820. Min Act: -0.0000

Data Index: 462044 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.8299. Min Act: -0.0000

Data Index: 859306 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.8054. Min Act: -0.0000

Data Index: 802011 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.7718. Min Act: 0.0000

Data Index: 1250301 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.9234. Min Act: -0.0000

Data Index: 1168893 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.9793. Min Act: -0.0000

Data Index: 320275 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.6446. Min Act: -0.0000

Data Index: 1136037 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.4726. Min Act: -0.0000

Data Index: 515361 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.1894. Min Act: -0.0000

Data Index: 686506 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.1349. Min Act: -0.0000

Data Index: 932236 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.4784. Min Act: -0.0000

Data Index: 498767 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.2567. Min Act: -0.0000

Data Index: 1274777 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.0291. Min Act: -0.0000

Data Index: 1355095 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.1295. Min Act: -0.0000

Data Index: 847525 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 4.4995. Min Range: -4.4995

Max Act: 3.1236. Min Act: -0.0000

Data Index: 434295 (C4 (Web Text))

Max Activating Token Index: 727