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

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

Neuron 5571 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.8940. Min Act: -0.0000

Data Index: 848273 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.5286. Min Act: -0.0000

Data Index: 510440 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.5044. Min Act: -0.0000

Data Index: 155230 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.5965. Min Act: -0.0000

Data Index: 847661 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.6276. Min Act: -0.0000

Data Index: 344924 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.3391. Min Act: -0.0000

Data Index: 162627 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.3205. Min Act: -0.0000

Data Index: 838648 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.3023. Min Act: -0.0000

Data Index: 487379 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.1740. Min Act: -0.0000

Data Index: 242723 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.1631. Min Act: -0.0000

Data Index: 10182 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.2628. Min Act: -0.0000

Data Index: 150483 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.2693. Min Act: -0.0000

Data Index: 723377 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.2699. Min Act: -0.0000

Data Index: 641111 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.2691. Min Act: -0.0000

Data Index: 871033 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.2621. Min Act: -0.0000

Data Index: 120900 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.1328. Min Act: -0.0000

Data Index: 146676 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.1098. Min Act: -0.0000

Data Index: 246468 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.0924. Min Act: -0.0000

Data Index: 1140449 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.2213. Min Act: -0.0000

Data Index: 746775 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 2.8940. Min Range: -2.8940

Max Act: 2.2058. Min Act: -0.0000

Data Index: 635836 (C4 (Web Text))

Max Activating Token Index: 536