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

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

Neuron 5035 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0002

Data Index: 472377 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0497. Min Act: -0.0002

Data Index: 698260 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1160687 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0438. Min Act: -0.0002

Data Index: 378877 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1487864 (Python Code)

Max Activating Token Index: 492

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0436. Min Act: -0.0002

Data Index: 342123 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1407929 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1306790 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1173618 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0402. Min Act: -0.0002

Data Index: 397030 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1373976 (Python Code)

Max Activating Token Index: 352

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0398. Min Act: -0.0002

Data Index: 100626 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1611405 (Python Code)

Max Activating Token Index: 311

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1655241 (Python Code)

Max Activating Token Index: 659

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1579773 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0399. Min Act: -0.0002

Data Index: 693017 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1453432 (Python Code)

Max Activating Token Index: 141

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1538750 (Python Code)

Max Activating Token Index: 386

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1628628 (Python Code)

Max Activating Token Index: 540

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1400075 (Python Code)

Max Activating Token Index: 548