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

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

Neuron 778 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4796. Min Act: -0.0000

Data Index: 513234 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4727. Min Act: -0.0000

Data Index: 176072 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4722. Min Act: -0.0000

Data Index: 418340 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4499. Min Act: -0.0000

Data Index: 955631 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4422. Min Act: -0.0000

Data Index: 100605 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4681. Min Act: -0.0000

Data Index: 684164 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4697. Min Act: -0.0000

Data Index: 754712 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4472. Min Act: -0.0000

Data Index: 869297 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4210. Min Act: -0.0000

Data Index: 969758 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4451. Min Act: -0.0000

Data Index: 810124 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4277. Min Act: -0.0000

Data Index: 395415 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4261. Min Act: -0.0000

Data Index: 264005 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4058. Min Act: -0.0000

Data Index: 146762 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1074385 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1144145 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4440. Min Act: -0.0000

Data Index: 981868 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4249. Min Act: -0.0000

Data Index: 750547 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1037271 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1050220 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4044. Min Act: -0.0000

Data Index: 708949 (C4 (Web Text))

Max Activating Token Index: 866