Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4131 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.4513. Min Range: -4.4513

Max Act: 4.4513. Min Act: -0.0000

Data Index: 1252493 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 4.4513. Min Range: -4.4513

Max Act: 3.9941. Min Act: -0.0000

Data Index: 1020060 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 4.4513. Min Range: -4.4513

Max Act: 3.8606. Min Act: -0.0000

Data Index: 872746 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 4.4513. Min Range: -4.4513

Max Act: 3.4585. Min Act: -0.0000

Data Index: 765816 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 4.4513. Min Range: -4.4513

Max Act: 2.9661. Min Act: -0.0000

Data Index: 665942 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 4.4513. Min Range: -4.4513

Max Act: 3.2494. Min Act: -0.0000

Data Index: 287156 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 4.4513. Min Range: -4.4513

Max Act: 3.4570. Min Act: -0.0000

Data Index: 408754 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 4.4513. Min Range: -4.4513

Max Act: 3.4510. Min Act: -0.0000

Data Index: 180198 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 4.4513. Min Range: -4.4513

Max Act: 3.2543. Min Act: -0.0000

Data Index: 1275383 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 4.4513. Min Range: -4.4513

Max Act: 3.0848. Min Act: -0.0000

Data Index: 637958 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 4.4513. Min Range: -4.4513

Max Act: 2.9503. Min Act: -0.0000

Data Index: 1176589 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 4.4513. Min Range: -4.4513

Max Act: 3.1566. Min Act: -0.0000

Data Index: 361327 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 4.4513. Min Range: -4.4513

Max Act: 3.1327. Min Act: -0.0000

Data Index: 938989 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 4.4513. Min Range: -4.4513

Max Act: 2.9819. Min Act: -0.0000

Data Index: 504412 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 4.4513. Min Range: -4.4513

Max Act: 2.8075. Min Act: -0.0000

Data Index: 711875 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 4.4513. Min Range: -4.4513

Max Act: 2.9090. Min Act: -0.0000

Data Index: 1142702 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 4.4513. Min Range: -4.4513

Max Act: 2.8118. Min Act: -0.0000

Data Index: 37512 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 4.4513. Min Range: -4.4513

Max Act: 2.9513. Min Act: -0.0000

Data Index: 1165618 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 4.4513. Min Range: -4.4513

Max Act: 2.9049. Min Act: -0.0000

Data Index: 831948 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 4.4513. Min Range: -4.4513

Max Act: 3.0173. Min Act: -0.0000

Data Index: 227044 (C4 (Web Text))

Max Activating Token Index: 242