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

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

Neuron 546 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.1250. Min Act: -0.0000

Data Index: 379968 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0820. Min Act: -0.0000

Data Index: 801821 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9575. Min Act: -0.0000

Data Index: 316313 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9898. Min Act: -0.0000

Data Index: 87481 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1109543 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9902. Min Act: -0.0000

Data Index: 621268 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9399. Min Act: -0.0000

Data Index: 747331 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0169. Min Act: -0.0000

Data Index: 231019 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9613. Min Act: -0.0000

Data Index: 638020 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9599. Min Act: -0.0000

Data Index: 76398 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8990. Min Act: -0.0000

Data Index: 494425 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9533. Min Act: -0.0000

Data Index: 514958 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9592. Min Act: -0.0000

Data Index: 459079 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9711. Min Act: -0.0000

Data Index: 786225 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8965. Min Act: -0.0000

Data Index: 830627 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1220268 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8978. Min Act: -0.0000

Data Index: 319320 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8670. Min Act: -0.0000

Data Index: 18403 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1202878 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8626. Min Act: -0.0000

Data Index: 932877 (C4 (Web Text))

Max Activating Token Index: 677