Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1574 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1064081 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1460581 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5693. Min Act: -0.0000

Data Index: 103213 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5635. Min Act: -0.0000

Data Index: 442582 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5985. Min Act: -0.0000

Data Index: 79180 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5759. Min Act: -0.0000

Data Index: 985050 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1974854 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5708. Min Act: -0.0000

Data Index: 316777 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1532433 (The Pile)

Max Activating Token Index: 132

Text #9

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5880. Min Act: -0.0000

Data Index: 392233 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1233025 (The Pile)

Max Activating Token Index: 575

Text #11

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5809. Min Act: -0.0000

Data Index: 674216 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1065002 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1977849 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5574. Min Act: -0.0000

Data Index: 568481 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1394723 (The Pile)

Max Activating Token Index: 937

Text #16

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1305727 (The Pile)

Max Activating Token Index: 476

Text #17

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5691. Min Act: -0.0000

Data Index: 135493 (The Pile)

Max Activating Token Index: 677

Text #18

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5438. Min Act: -0.0000

Data Index: 457945 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5436. Min Act: -0.0000

Data Index: 413075 (The Pile)

Max Activating Token Index: 801