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

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

Neuron 1822 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1355682 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.8272. Min Act: -0.0000

Data Index: 288333 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.8334. Min Act: -0.0000

Data Index: 559808 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.7941. Min Act: -0.0000

Data Index: 222070 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.7578. Min Act: -0.0000

Data Index: 281730 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6762. Min Act: -0.0000

Data Index: 185501 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.7174. Min Act: -0.0000

Data Index: 284655 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.7357. Min Act: -0.0000

Data Index: 807808 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1054439 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6957. Min Act: -0.0000

Data Index: 960065 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1309816 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1008002 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1282053 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6459. Min Act: -0.0000

Data Index: 829352 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6446. Min Act: -0.0000

Data Index: 289332 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6717. Min Act: -0.0000

Data Index: 483743 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6877. Min Act: -0.0000

Data Index: 285287 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1005478 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6422. Min Act: -0.0000

Data Index: 112539 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6155. Min Act: -0.0000

Data Index: 221078 (C4 (Web Text))

Max Activating Token Index: 197