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

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

Neuron 5580 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4846. Min Act: 0.0000

Data Index: 122008 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4018. Min Act: -0.0000

Data Index: 784162 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4032. Min Act: -0.0000

Data Index: 872764 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3843. Min Act: -0.0000

Data Index: 945069 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3809. Min Act: -0.0000

Data Index: 281287 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3620. Min Act: -0.0000

Data Index: 825013 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3571. Min Act: -0.0000

Data Index: 51093 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3622. Min Act: -0.0000

Data Index: 759454 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1048549 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3520. Min Act: 0.0000

Data Index: 659337 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1189014 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3302. Min Act: -0.0000

Data Index: 29769 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3160. Min Act: -0.0000

Data Index: 278961 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3175. Min Act: 0.0000

Data Index: 652757 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1163145 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1512598 (Python Code)

Max Activating Token Index: 965

Text #16

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3087. Min Act: -0.0000

Data Index: 445772 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3268. Min Act: -0.0000

Data Index: 207650 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3234. Min Act: 0.0000

Data Index: 1184148 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3102. Min Act: 0.0000

Data Index: 658457 (C4 (Web Text))

Max Activating Token Index: 562