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

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

Neuron 5702 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.6373. Min Act: -0.0001

Data Index: 1213395 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.3461. Min Act: -0.0001

Data Index: 1212367 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.4019. Min Act: -0.0001

Data Index: 661914 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.5662. Min Act: -0.0001

Data Index: 12894 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.2919. Min Act: -0.0001

Data Index: 690198 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.2624. Min Act: -0.0001

Data Index: 535153 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.4520. Min Act: -0.0001

Data Index: 620868 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.3104. Min Act: -0.0001

Data Index: 1317582 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.3239. Min Act: -0.0001

Data Index: 490691 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.2656. Min Act: -0.0001

Data Index: 1341762 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.3184. Min Act: -0.0001

Data Index: 564807 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.1454. Min Act: -0.0001

Data Index: 305253 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.2549. Min Act: -0.0001

Data Index: 783613 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.1205. Min Act: -0.0001

Data Index: 1126290 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.3474. Min Act: -0.0001

Data Index: 203313 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.1875. Min Act: -0.0001

Data Index: 1339996 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.0459. Min Act: -0.0001

Data Index: 256980 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.1305. Min Act: -0.0001

Data Index: 329673 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.1968. Min Act: -0.0001

Data Index: 415717 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 1.6373. Min Range: -1.6373

Max Act: 1.1498. Min Act: -0.0001

Data Index: 586320 (C4 (Web Text))

Max Activating Token Index: 395