Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 228 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0001

Data Index: 543499 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0389. Min Act: -0.0001

Data Index: 1291121 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1297139 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0374. Min Act: -0.0001

Data Index: 633006 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1116564 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0431. Min Act: -0.0001

Data Index: 858140 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0376. Min Act: -0.0001

Data Index: 167334 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0402. Min Act: -0.0001

Data Index: 779562 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1040093 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0385. Min Act: -0.0001

Data Index: 786106 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1048411 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0350. Min Act: -0.0001

Data Index: 715484 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0357. Min Act: -0.0001

Data Index: 175760 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0367. Min Act: -0.0001

Data Index: 581944 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0398. Min Act: -0.0001

Data Index: 468940 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1469593 (Python Code)

Max Activating Token Index: 276

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0366. Min Act: -0.0001

Data Index: 164033 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0352. Min Act: -0.0001

Data Index: 876670 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0320. Min Act: -0.0001

Data Index: 639355 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0371. Min Act: -0.0001

Data Index: 474938 (C4 (Web Text))

Max Activating Token Index: 495