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

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

Neuron 3487 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.8366. Min Act: -0.0000

Data Index: 651368 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7822. Min Act: -0.0000

Data Index: 596598 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7707. Min Act: -0.0000

Data Index: 354214 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7268. Min Act: -0.0000

Data Index: 7207 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6751. Min Act: -0.0000

Data Index: 133949 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1056369 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1265525 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7208. Min Act: -0.0000

Data Index: 535451 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7459. Min Act: -0.0000

Data Index: 270986 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6609. Min Act: -0.0000

Data Index: 63251 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1105113 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6485. Min Act: -0.0001

Data Index: 1359065 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7374. Min Act: -0.0000

Data Index: 755233 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6787. Min Act: -0.0000

Data Index: 623290 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6533. Min Act: -0.0000

Data Index: 179485 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6641. Min Act: -0.0000

Data Index: 945275 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6573. Min Act: -0.0000

Data Index: 297872 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6124. Min Act: -0.0000

Data Index: 449060 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.5918. Min Act: -0.0000

Data Index: 836013 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6254. Min Act: -0.0000

Data Index: 944592 (C4 (Web Text))

Max Activating Token Index: 160