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

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

Neuron 686 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7927. Min Act: -0.0003

Data Index: 379140 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7036. Min Act: -0.0003

Data Index: 308369 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6777. Min Act: -0.0003

Data Index: 1344228 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7299. Min Act: -0.0003

Data Index: 1031256 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6472. Min Act: -0.0003

Data Index: 1132587 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7280. Min Act: -0.0003

Data Index: 1334352 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5756. Min Act: -0.0003

Data Index: 919136 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6604. Min Act: -0.0003

Data Index: 981468 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5976. Min Act: -0.0003

Data Index: 753001 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5948. Min Act: -0.0003

Data Index: 1242487 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5970. Min Act: -0.0004

Data Index: 108245 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5748. Min Act: -0.0003

Data Index: 600021 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5482. Min Act: -0.0003

Data Index: 23928 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5858. Min Act: -0.0003

Data Index: 561238 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5795. Min Act: -0.0003

Data Index: 656828 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5982. Min Act: -0.0003

Data Index: 100830 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5618. Min Act: -0.0003

Data Index: 634354 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5985. Min Act: -0.0003

Data Index: 985728 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5545. Min Act: -0.0003

Data Index: 17900 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6099. Min Act: -0.0003

Data Index: 701587 (C4 (Web Text))

Max Activating Token Index: 145