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

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

Neuron 5687 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0417. Min Range: -5.0417

Max Act: 5.0417. Min Act: -0.0001

Data Index: 331408 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.8494. Min Act: -0.0001

Data Index: 93204 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.6780. Min Act: -0.0001

Data Index: 523059 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.6931. Min Act: -0.0001

Data Index: 474572 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.0491. Min Act: -0.0001

Data Index: 1118506 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.1687. Min Act: -0.0001

Data Index: 1231199 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.2656. Min Act: -0.0001

Data Index: 349880 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.1395. Min Act: -0.0001

Data Index: 408365 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.1337. Min Act: -0.0001

Data Index: 1118947 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.0836. Min Act: -0.0001

Data Index: 571529 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.2369. Min Act: -0.0001

Data Index: 623802 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.0612. Min Act: -0.0001

Data Index: 58371 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 5.0417. Min Range: -5.0417

Max Act: 3.5406. Min Act: -0.0001

Data Index: 37274 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 5.0417. Min Range: -5.0417

Max Act: 3.9722. Min Act: -0.0001

Data Index: 276945 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 5.0417. Min Range: -5.0417

Max Act: 3.8960. Min Act: -0.0001

Data Index: 635900 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 5.0417. Min Range: -5.0417

Max Act: 4.2400. Min Act: -0.0001

Data Index: 350048 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 5.0417. Min Range: -5.0417

Max Act: 3.6535. Min Act: -0.0001

Data Index: 643355 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 5.0417. Min Range: -5.0417

Max Act: 3.7856. Min Act: -0.0001

Data Index: 1313600 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 5.0417. Min Range: -5.0417

Max Act: 3.7511. Min Act: -0.0001

Data Index: 771650 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 5.0417. Min Range: -5.0417

Max Act: 3.7373. Min Act: -0.0001

Data Index: 1211650 (C4 (Web Text))

Max Activating Token Index: 41