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

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

Neuron 3835 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: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1161732 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0492. Min Act: -0.0002

Data Index: 301260 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0487. Min Act: -0.0001

Data Index: 970254 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0471. Min Act: -0.0001

Data Index: 124786 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0468. Min Act: -0.0001

Data Index: 652325 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0468. Min Act: -0.0002

Data Index: 324378 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1225272 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0439. Min Act: -0.0002

Data Index: 10460 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0436. Min Act: -0.0002

Data Index: 343023 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1022653 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0424. Min Act: -0.0001

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1325784 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1060412 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0414. Min Act: -0.0001

Data Index: 1288550 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0413. Min Act: -0.0002

Data Index: 10116 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0397. Min Act: -0.0001

Data Index: 217149 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0407. Min Act: -0.0002

Data Index: 624041 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0408. Min Act: -0.0002

Data Index: 11016 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0401. Min Act: -0.0001

Data Index: 900398 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0404. Min Act: -0.0002

Data Index: 47030 (C4 (Web Text))

Max Activating Token Index: 160