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

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

Neuron 5094 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.6379. Min Act: -0.0000

Data Index: 1199967 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.6539. Min Act: -0.0000

Data Index: 1282856 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.5121. Min Act: -0.0000

Data Index: 230686 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.2947. Min Act: -0.0000

Data Index: 887864 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.1502. Min Act: -0.0000

Data Index: 69775 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.1217. Min Act: -0.0000

Data Index: 597537 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.1984. Min Act: -0.0000

Data Index: 1040515 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.1672. Min Act: -0.0000

Data Index: 534645 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.1665. Min Act: -0.0000

Data Index: 698024 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.0773. Min Act: -0.0000

Data Index: 688022 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 1.6539. Min Range: -1.6539

Max Act: 0.9981. Min Act: -0.0000

Data Index: 242652 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.0597. Min Act: -0.0000

Data Index: 8375 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 1.6539. Min Range: -1.6539

Max Act: 0.9890. Min Act: -0.0000

Data Index: 901843 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.0408. Min Act: -0.0000

Data Index: 481276 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1305206 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.0982. Min Act: -0.0000

Data Index: 816734 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.0936. Min Act: -0.0000

Data Index: 755366 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 1.6539. Min Range: -1.6539

Max Act: 0.9662. Min Act: -0.0000

Data Index: 105852 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 1.6539. Min Range: -1.6539

Max Act: 0.9689. Min Act: -0.0000

Data Index: 412581 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 1.6539. Min Range: -1.6539

Max Act: 1.0090. Min Act: -0.0000

Data Index: 424446 (C4 (Web Text))

Max Activating Token Index: 480