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

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

Neuron 3120 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: 0.5684. Min Range: -0.5684

Max Act: 0.5684. Min Act: -0.0000

Data Index: 999537 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5319. Min Act: -0.0000

Data Index: 404896 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5210. Min Act: -0.0000

Data Index: 566592 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5286. Min Act: -0.0000

Data Index: 372820 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5060. Min Act: -0.0000

Data Index: 485998 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4929. Min Act: -0.0000

Data Index: 547115 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4915. Min Act: -0.0000

Data Index: 837398 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1120031 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1084353 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4803. Min Act: -0.0000

Data Index: 922249 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4913. Min Act: -0.0000

Data Index: 743697 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4864. Min Act: 0.0000

Data Index: 1354743 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4858. Min Act: -0.0000

Data Index: 30991 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5029. Min Act: 0.0000

Data Index: 347534 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1172111 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5017. Min Act: -0.0000

Data Index: 912811 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4842. Min Act: -0.0000

Data Index: 261388 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4824. Min Act: -0.0000

Data Index: 224965 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1133445 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4718. Min Act: -0.0000

Data Index: 376143 (C4 (Web Text))

Max Activating Token Index: 590