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

Dataset: The Pile

Neuron 2956 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.7791. Min Act: -0.0000

Data Index: 165506 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.6288. Min Act: -0.0000

Data Index: 1717612 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.4588. Min Act: -0.0000

Data Index: 1644490 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.4503. Min Act: -0.0000

Data Index: 501244 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.4173. Min Act: -0.0000

Data Index: 1793529 (The Pile)

Max Activating Token Index: 796

Text #5

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.6680. Min Act: -0.0000

Data Index: 440985 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.4599. Min Act: -0.0000

Data Index: 1470004 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1327521 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.2823. Min Act: -0.0000

Data Index: 1593528 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1325719 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.6797. Min Act: -0.0000

Data Index: 661270 (The Pile)

Max Activating Token Index: 788

Text #11

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.3524. Min Act: -0.0000

Data Index: 172461 (The Pile)

Max Activating Token Index: 94

Text #12

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.4649. Min Act: -0.0000

Data Index: 916615 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.3020. Min Act: -0.0000

Data Index: 1284075 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.2408. Min Act: -0.0000

Data Index: 362552 (The Pile)

Max Activating Token Index: 1005

Text #15

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.3485. Min Act: -0.0000

Data Index: 1721703 (The Pile)

Max Activating Token Index: 209

Text #16

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.3401. Min Act: -0.0000

Data Index: 892943 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.2218. Min Act: -0.0000

Data Index: 106231 (The Pile)

Max Activating Token Index: 485

Text #18

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.2931. Min Act: -0.0000

Data Index: 1625570 (The Pile)

Max Activating Token Index: 84

Text #19

Max Range: 1.7791. Min Range: -1.7791

Max Act: 1.1933. Min Act: -0.0000

Data Index: 292268 (The Pile)

Max Activating Token Index: 783