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

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

Neuron 4035 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: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0001

Data Index: 962958 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0469. Min Act: -0.0000

Data Index: 985053 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1008201 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0435. Min Act: -0.0001

Data Index: 501637 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0424. Min Act: -0.0001

Data Index: 770203 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0420. Min Act: -0.0000

Data Index: 836447 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0363. Min Act: -0.0000

Data Index: 544176 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0399. Min Act: -0.0001

Data Index: 51143 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0396. Min Act: -0.0001

Data Index: 838140 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1304265 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0420. Min Act: -0.0000

Data Index: 688693 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0381. Min Act: -0.0001

Data Index: 752413 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0376. Min Act: -0.0001

Data Index: 748868 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0352. Min Act: -0.0000

Data Index: 507434 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0363. Min Act: -0.0001

Data Index: 330535 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0367. Min Act: -0.0001

Data Index: 572320 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0342. Min Act: -0.0001

Data Index: 962974 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0328. Min Act: -0.0001

Data Index: 36139 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0350. Min Act: -0.0001

Data Index: 355070 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0337. Min Act: -0.0001

Data Index: 609094 (C4 (Web Text))

Max Activating Token Index: 95