Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2998 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1050416 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3693. Min Act: -0.0000

Data Index: 528277 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1217104 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3372. Min Act: -0.0000

Data Index: 412207 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3373. Min Act: -0.0000

Data Index: 639761 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3252. Min Act: -0.0000

Data Index: 623827 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3333. Min Act: -0.0000

Data Index: 305258 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3047. Min Act: -0.0000

Data Index: 119422 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2838. Min Act: -0.0000

Data Index: 218010 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3002. Min Act: -0.0000

Data Index: 475282 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2835. Min Act: -0.0000

Data Index: 471115 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2864. Min Act: -0.0000

Data Index: 643736 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2845. Min Act: -0.0000

Data Index: 978051 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1301964 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2733. Min Act: -0.0000

Data Index: 197706 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2707. Min Act: -0.0000

Data Index: 320376 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2784. Min Act: -0.0000

Data Index: 216614 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2858. Min Act: -0.0000

Data Index: 894997 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2645. Min Act: -0.0000

Data Index: 765203 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2739. Min Act: -0.0000

Data Index: 560163 (C4 (Web Text))

Max Activating Token Index: 149