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

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

Neuron 2070 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2879. Min Act: -0.0001

Data Index: 20140 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2737. Min Act: -0.0001

Data Index: 1208139 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2694. Min Act: -0.0001

Data Index: 535431 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2659. Min Act: -0.0001

Data Index: 468317 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2498. Min Act: -0.0001

Data Index: 560096 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2590. Min Act: -0.0001

Data Index: 1197701 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2540. Min Act: -0.0001

Data Index: 97752 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2543. Min Act: -0.0001

Data Index: 211405 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2518. Min Act: -0.0001

Data Index: 26449 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2507. Min Act: -0.0001

Data Index: 97211 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2501. Min Act: -0.0001

Data Index: 1195018 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2324. Min Act: -0.0001

Data Index: 786573 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2391. Min Act: -0.0001

Data Index: 898472 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2387. Min Act: -0.0001

Data Index: 146714 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2452. Min Act: -0.0001

Data Index: 1359613 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2386. Min Act: -0.0001

Data Index: 85976 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2448. Min Act: -0.0001

Data Index: 506124 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2273. Min Act: -0.0001

Data Index: 376122 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2310. Min Act: -0.0001

Data Index: 747693 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.2879. Min Range: -0.2879

Max Act: 0.2228. Min Act: -0.0001

Data Index: 1018728 (C4 (Web Text))

Max Activating Token Index: 397