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

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

Neuron 4445 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1097880 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.5277. Min Act: -0.0000

Data Index: 288694 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.3617. Min Act: -0.0000

Data Index: 13627 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.5098. Min Act: -0.0000

Data Index: 936847 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.3690. Min Act: -0.0000

Data Index: 1008308 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.2202. Min Act: -0.0000

Data Index: 635909 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1177835 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.1916. Min Act: -0.0000

Data Index: 728986 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.0809. Min Act: -0.0000

Data Index: 105721 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.1025. Min Act: 0.0000

Data Index: 653375 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.1467. Min Act: -0.0000

Data Index: 693901 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.0463. Min Act: -0.0000

Data Index: 143285 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1143161 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.0375. Min Act: -0.0000

Data Index: 1250318 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 1.5277. Min Range: -1.5277

Max Act: 1.0106. Min Act: -0.0000

Data Index: 149170 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 1.5277. Min Range: -1.5277

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1290214 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 1.5277. Min Range: -1.5277

Max Act: 0.9845. Min Act: -0.0000

Data Index: 680645 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.5277. Min Range: -1.5277

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1329011 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 1.5277. Min Range: -1.5277

Max Act: 0.9129. Min Act: -0.0000

Data Index: 875520 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 1.5277. Min Range: -1.5277

Max Act: 0.9179. Min Act: -0.0000

Data Index: 545143 (C4 (Web Text))

Max Activating Token Index: 789