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

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

Neuron 4890 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5479. Min Act: -0.0000

Data Index: 836155 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4993. Min Act: -0.0000

Data Index: 113642 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5280. Min Act: -0.0000

Data Index: 922870 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5065. Min Act: -0.0000

Data Index: 150565 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4913. Min Act: -0.0000

Data Index: 379920 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5139. Min Act: -0.0000

Data Index: 95203 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5331. Min Act: -0.0000

Data Index: 12850 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4897. Min Act: -0.0000

Data Index: 958543 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4736. Min Act: -0.0000

Data Index: 114119 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1273892 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4680. Min Act: -0.0000

Data Index: 509199 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4374. Min Act: -0.0000

Data Index: 691867 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4810. Min Act: -0.0000

Data Index: 195915 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4679. Min Act: -0.0000

Data Index: 906892 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4601. Min Act: -0.0000

Data Index: 651764 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1222289 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1357935 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1288381 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4598. Min Act: -0.0000

Data Index: 204598 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4613. Min Act: -0.0000

Data Index: 407603 (C4 (Web Text))

Max Activating Token Index: 357