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

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

Neuron 5081 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0626. Min Act: -0.0002

Data Index: 97280 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1352905 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0002

Data Index: 916194 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0521. Min Act: -0.0002

Data Index: 332766 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0509. Min Act: -0.0002

Data Index: 583972 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0513. Min Act: -0.0002

Data Index: 507788 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0491. Min Act: -0.0002

Data Index: 902992 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0489. Min Act: -0.0002

Data Index: 170725 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0468. Min Act: -0.0002

Data Index: 765742 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0460. Min Act: -0.0002

Data Index: 179864 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1245051 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1201785 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0466. Min Act: -0.0002

Data Index: 852264 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1307295 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0461. Min Act: -0.0002

Data Index: 872771 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1275584 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0456. Min Act: -0.0002

Data Index: 228319 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1300078 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0454. Min Act: -0.0002

Data Index: 703902 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0452. Min Act: -0.0002

Data Index: 519687 (C4 (Web Text))

Max Activating Token Index: 221