Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 850 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0437. Min Act: -0.0004

Data Index: 1162557 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0359. Min Act: -0.0004

Data Index: 965867 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0333. Min Act: -0.0004

Data Index: 989023 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0399. Min Act: -0.0004

Data Index: 568381 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1235008 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0343. Min Act: -0.0004

Data Index: 980109 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0352. Min Act: -0.0004

Data Index: 1357 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0307. Min Act: -0.0004

Data Index: 867128 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0327. Min Act: -0.0004

Data Index: 780446 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0321. Min Act: -0.0004

Data Index: 588520 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0314. Min Act: -0.0004

Data Index: 803909 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0308. Min Act: -0.0004

Data Index: 340952 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0297. Min Act: -0.0004

Data Index: 1034649 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1210024 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0287. Min Act: -0.0004

Data Index: 392294 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0283. Min Act: -0.0004

Data Index: 1017802 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0272. Min Act: -0.0004

Data Index: 961564 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0273. Min Act: -0.0004

Data Index: 1310512 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0291. Min Act: -0.0004

Data Index: 698810 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0286. Min Act: -0.0004

Data Index: 1270470 (C4 (Web Text))

Max Activating Token Index: 228