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

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

Neuron 5834 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2575. Min Range: -4.2575

Max Act: 4.2575. Min Act: -0.0000

Data Index: 1356815 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.9536. Min Act: -0.0000

Data Index: 205844 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 4.2575. Min Range: -4.2575

Max Act: 4.1478. Min Act: -0.0000

Data Index: 98023 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.7664. Min Act: -0.0000

Data Index: 231741 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.2803. Min Act: -0.0000

Data Index: 420004 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.6538. Min Act: -0.0000

Data Index: 1056529 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.8858. Min Act: -0.0000

Data Index: 496707 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.7410. Min Act: -0.0000

Data Index: 674291 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.6486. Min Act: -0.0000

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.7230. Min Act: -0.0000

Data Index: 319511 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.6056. Min Act: -0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.4406. Min Act: -0.0000

Data Index: 1062725 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.6178. Min Act: -0.0000

Data Index: 641986 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.6294. Min Act: -0.0000

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.5299. Min Act: -0.0000

Data Index: 178279 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.4836. Min Act: -0.0000

Data Index: 428818 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.3746. Min Act: -0.0000

Data Index: 283743 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.4204. Min Act: -0.0000

Data Index: 1137447 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.5146. Min Act: -0.0000

Data Index: 1582951 (Python Code)

Max Activating Token Index: 78

Text #19

Max Range: 4.2575. Min Range: -4.2575

Max Act: 2.3406. Min Act: -0.0000

Data Index: 882184 (C4 (Web Text))

Max Activating Token Index: 879