Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3078 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.5320. Min Act: -0.0001

Data Index: 484199 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.4007. Min Act: -0.0001

Data Index: 1491726 (Python Code)

Max Activating Token Index: 511

Text #2

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.3630. Min Act: -0.0000

Data Index: 286009 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.3319. Min Act: -0.0000

Data Index: 586053 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.3519. Min Act: -0.0001

Data Index: 182422 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.2618. Min Act: -0.0001

Data Index: 1575071 (Python Code)

Max Activating Token Index: 816

Text #6

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.3027. Min Act: -0.0001

Data Index: 1259343 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.2822. Min Act: -0.0001

Data Index: 1517503 (Python Code)

Max Activating Token Index: 306

Text #8

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.2802. Min Act: -0.0000

Data Index: 204555 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.2399. Min Act: -0.0000

Data Index: 445263 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.2485. Min Act: -0.0001

Data Index: 370341 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.2498. Min Act: -0.0000

Data Index: 809724 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.2457. Min Act: -0.0001

Data Index: 1487862 (Python Code)

Max Activating Token Index: 249

Text #13

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.2436. Min Act: -0.0000

Data Index: 693163 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.2331. Min Act: -0.0001

Data Index: 1163119 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.2707. Min Act: -0.0001

Data Index: 665946 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.1624. Min Act: -0.0001

Data Index: 1551260 (Python Code)

Max Activating Token Index: 288

Text #17

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.1999. Min Act: -0.0000

Data Index: 653763 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.1603. Min Act: -0.0000

Data Index: 764777 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.5320. Min Range: -1.5320

Max Act: 1.1781. Min Act: -0.0000

Data Index: 639152 (C4 (Web Text))

Max Activating Token Index: 913