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

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

Neuron 4656 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: 2.1925. Min Range: -2.1925

Max Act: 2.1925. Min Act: -0.0000

Data Index: 1268665 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.9015. Min Act: -0.0000

Data Index: 765148 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.9483. Min Act: -0.0000

Data Index: 1226993 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.1712. Min Act: -0.0000

Data Index: 1148978 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0263. Min Act: -0.0000

Data Index: 918713 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.8930. Min Act: -0.0000

Data Index: 659217 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.8697. Min Act: -0.0000

Data Index: 645832 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.7977. Min Act: -0.0000

Data Index: 1294471 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.7941. Min Act: -0.0000

Data Index: 1170785 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.6791. Min Act: -0.0000

Data Index: 762273 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.8686. Min Act: -0.0000

Data Index: 473292 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.7654. Min Act: -0.0000

Data Index: 94804 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.7627. Min Act: -0.0000

Data Index: 1273323 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.7189. Min Act: -0.0000

Data Index: 396649 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.6334. Min Act: -0.0000

Data Index: 1456599 (Python Code)

Max Activating Token Index: 198

Text #15

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.7114. Min Act: -0.0000

Data Index: 343357 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.6028. Min Act: -0.0000

Data Index: 571074 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.7710. Min Act: -0.0000

Data Index: 777332 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.7586. Min Act: -0.0000

Data Index: 123969 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 2.1925. Min Range: -2.1925

Max Act: 1.5631. Min Act: -0.0000

Data Index: 671416 (C4 (Web Text))

Max Activating Token Index: 90