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

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

Neuron 2633 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.8742. Min Act: -0.0000

Data Index: 249466 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.2570. Min Act: -0.0000

Data Index: 863285 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.7350. Min Act: -0.0000

Data Index: 491160 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.6815. Min Act: -0.0000

Data Index: 390213 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.7066. Min Act: -0.0000

Data Index: 429770 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.6690. Min Act: -0.0000

Data Index: 434500 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.5445. Min Act: -0.0000

Data Index: 1000222 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.6438. Min Act: -0.0000

Data Index: 962259 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.5336. Min Act: -0.0000

Data Index: 37057 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.4235. Min Act: -0.0000

Data Index: 768197 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.1776. Min Act: -0.0000

Data Index: 811164 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.0665. Min Act: -0.0000

Data Index: 510030 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.1058. Min Act: -0.0000

Data Index: 358472 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.3683. Min Act: -0.0000

Data Index: 1255287 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.3242. Min Act: -0.0000

Data Index: 464661 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.2101. Min Act: -0.0000

Data Index: 381473 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.1631. Min Act: -0.0000

Data Index: 373215 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.0629. Min Act: -0.0000

Data Index: 80509 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.1355. Min Act: -0.0000

Data Index: 268254 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 3.8742. Min Range: -3.8742

Max Act: 2.2305. Min Act: -0.0000

Data Index: 647685 (C4 (Web Text))

Max Activating Token Index: 709