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

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

Neuron 1348 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.6414. Min Act: -0.0000

Data Index: 580423 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1169727 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5802. Min Act: -0.0000

Data Index: 193677 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5840. Min Act: -0.0000

Data Index: 465512 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1138518 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5388. Min Act: -0.0000

Data Index: 728466 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5159. Min Act: -0.0000

Data Index: 578888 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1047017 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5350. Min Act: -0.0000

Data Index: 950427 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4233. Min Act: -0.0000

Data Index: 29060 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4182. Min Act: -0.0000

Data Index: 143702 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4292. Min Act: -0.0000

Data Index: 754274 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4251. Min Act: -0.0000

Data Index: 738070 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4347. Min Act: -0.0000

Data Index: 89092 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4310. Min Act: -0.0000

Data Index: 941236 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4473. Min Act: -0.0000

Data Index: 830482 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4361. Min Act: 0.0000

Data Index: 877032 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4354. Min Act: -0.0000

Data Index: 410041 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.3996. Min Act: -0.0000

Data Index: 528298 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1313699 (C4 (Web Text))

Max Activating Token Index: 896