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

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

Neuron 2713 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: 1.4809. Min Range: -1.4809

Max Act: 1.4809. Min Act: -0.0000

Data Index: 826823 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 1.4809. Min Range: -1.4809

Max Act: 1.0087. Min Act: -0.0000

Data Index: 462031 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.9785. Min Act: -0.0000

Data Index: 551956 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.9925. Min Act: -0.0000

Data Index: 518548 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.9493. Min Act: -0.0000

Data Index: 519976 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.9077. Min Act: -0.0000

Data Index: 344382 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.9353. Min Act: -0.0000

Data Index: 378611 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1295599 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1323235 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.9061. Min Act: -0.0000

Data Index: 377882 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.8837. Min Act: -0.0000

Data Index: 589067 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.8755. Min Act: -0.0000

Data Index: 627801 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.8148. Min Act: -0.0000

Data Index: 799669 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1039338 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.8523. Min Act: -0.0000

Data Index: 753009 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.8435. Min Act: -0.0000

Data Index: 909053 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.8419. Min Act: -0.0000

Data Index: 362239 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1150503 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.8314. Min Act: -0.0000

Data Index: 23362 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.4809. Min Range: -1.4809

Max Act: 0.7859. Min Act: -0.0000

Data Index: 57185 (C4 (Web Text))

Max Activating Token Index: 982