Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 79 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0005

Data Index: 498499 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0337. Min Act: -0.0005

Data Index: 1046099 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0336. Min Act: -0.0005

Data Index: 924391 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0318. Min Act: -0.0005

Data Index: 947558 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0336. Min Act: -0.0005

Data Index: 10605 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0303. Min Act: -0.0005

Data Index: 429123 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0303. Min Act: -0.0005

Data Index: 923750 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0296. Min Act: -0.0005

Data Index: 95072 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0297. Min Act: -0.0005

Data Index: 1245850 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0308. Min Act: -0.0005

Data Index: 654404 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0294. Min Act: -0.0005

Data Index: 900114 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0301. Min Act: -0.0005

Data Index: 1358389 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0281. Min Act: -0.0005

Data Index: 913350 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0323. Min Act: -0.0005

Data Index: 793670 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0303. Min Act: -0.0005

Data Index: 637644 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0307. Min Act: -0.0005

Data Index: 806718 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0284. Min Act: -0.0005

Data Index: 341387 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0278. Min Act: -0.0005

Data Index: 532959 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0284. Min Act: -0.0005

Data Index: 594409 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0270. Min Act: -0.0005

Data Index: 1044163 (C4 (Web Text))

Max Activating Token Index: 771