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

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

Neuron 4480 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0000

Data Index: 531982 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1189700 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1189157 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0469. Min Act: -0.0000

Data Index: 15199 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1315281 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0406. Min Act: -0.0001

Data Index: 165885 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0402. Min Act: -0.0001

Data Index: 983888 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0397. Min Act: -0.0000

Data Index: 304905 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0382. Min Act: -0.0000

Data Index: 597598 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1229223 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1215288 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0352. Min Act: -0.0001

Data Index: 20847 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1265073 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1359430 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0328. Min Act: -0.0000

Data Index: 59013 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0347. Min Act: -0.0001

Data Index: 870868 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0342. Min Act: -0.0000

Data Index: 731751 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0352. Min Act: -0.0001

Data Index: 268191 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0336. Min Act: -0.0001

Data Index: 890858 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0349. Min Act: -0.0001

Data Index: 741163 (C4 (Web Text))

Max Activating Token Index: 849