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

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

Neuron 789 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5576. Min Range: -2.5576

Max Act: 2.4209. Min Act: -0.0000

Data Index: 1018656 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 2.5576. Min Range: -2.5576

Max Act: 2.5576. Min Act: -0.0000

Data Index: 266022 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 2.5576. Min Range: -2.5576

Max Act: 2.1372. Min Act: -0.0000

Data Index: 1264737 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.9018. Min Act: -0.0000

Data Index: 1306269 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.9592. Min Act: -0.0000

Data Index: 1350060 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.8789. Min Act: -0.0000

Data Index: 551583 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.7772. Min Act: -0.0000

Data Index: 670397 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.8727. Min Act: -0.0000

Data Index: 196361 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.8261. Min Act: -0.0000

Data Index: 1342294 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.7339. Min Act: -0.0000

Data Index: 83572 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.7941. Min Act: -0.0000

Data Index: 1073901 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.7396. Min Act: -0.0000

Data Index: 650071 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.7101. Min Act: -0.0000

Data Index: 316198 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.5608. Min Act: -0.0000

Data Index: 524816 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.6335. Min Act: -0.0000

Data Index: 1232373 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.6282. Min Act: -0.0000

Data Index: 497966 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.5866. Min Act: -0.0000

Data Index: 127776 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.5612. Min Act: -0.0000

Data Index: 524672 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.4880. Min Act: -0.0000

Data Index: 385653 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 2.5576. Min Range: -2.5576

Max Act: 1.6356. Min Act: -0.0000

Data Index: 1355547 (C4 (Web Text))

Max Activating Token Index: 338