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

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

Neuron 1285 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.3729. Min Act: -0.0003

Data Index: 661107 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.3044. Min Act: -0.0002

Data Index: 1246276 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.2436. Min Act: -0.0002

Data Index: 338573 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.1717. Min Act: -0.0002

Data Index: 112106 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.1351. Min Act: -0.0002

Data Index: 891400 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.1161. Min Act: -0.0002

Data Index: 307203 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.1279. Min Act: -0.0002

Data Index: 1070025 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.1427. Min Act: -0.0002

Data Index: 231203 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.1458. Min Act: -0.0002

Data Index: 1322719 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.0650. Min Act: -0.0002

Data Index: 721357 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.0471. Min Act: -0.0002

Data Index: 1618512 (Python Code)

Max Activating Token Index: 401

Text #11

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.0579. Min Act: -0.0002

Data Index: 383905 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.0162. Min Act: -0.0002

Data Index: 1217654 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.0130. Min Act: -0.0002

Data Index: 109010 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.0672. Min Act: -0.0002

Data Index: 599893 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.0063. Min Act: -0.0002

Data Index: 377365 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 10.3729. Min Range: -10.3729

Max Act: 10.0122. Min Act: -0.0002

Data Index: 1050516 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 10.3729. Min Range: -10.3729

Max Act: 9.9374. Min Act: -0.0002

Data Index: 102191 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 10.3729. Min Range: -10.3729

Max Act: 9.9826. Min Act: -0.0002

Data Index: 644371 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 10.3729. Min Range: -10.3729

Max Act: 9.9149. Min Act: -0.0002

Data Index: 717896 (C4 (Web Text))

Max Activating Token Index: 359