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

Dataset: The Pile

Neuron 4828 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.5070. Min Act: -0.0000

Data Index: 545937 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.4475. Min Act: -0.0000

Data Index: 1019051 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.3607. Min Act: -0.0000

Data Index: 68379 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.3467. Min Act: -0.0000

Data Index: 380238 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1624038 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.3428. Min Act: -0.0000

Data Index: 1145666 (The Pile)

Max Activating Token Index: 890

Text #6

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1898987 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1647. Min Act: -0.0000

Data Index: 705838 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.2134. Min Act: -0.0000

Data Index: 649656 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1125. Min Act: 0.0000

Data Index: 1345228 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1823. Min Act: -0.0000

Data Index: 886216 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1003. Min Act: -0.0000

Data Index: 152422 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.0205. Min Act: -0.0000

Data Index: 615730 (The Pile)

Max Activating Token Index: 509

Text #13

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1860048 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.0396. Min Act: -0.0000

Data Index: 726905 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 1.5070. Min Range: -1.5070

Max Act: 0.9789. Min Act: -0.0000

Data Index: 129518 (The Pile)

Max Activating Token Index: 478

Text #16

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.0723. Min Act: -0.0000

Data Index: 418119 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.0294. Min Act: -0.0000

Data Index: 514130 (The Pile)

Max Activating Token Index: 595

Text #18

Max Range: 1.5070. Min Range: -1.5070

Max Act: 1.0141. Min Act: -0.0000

Data Index: 786244 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 1.5070. Min Range: -1.5070

Max Act: 0.9835. Min Act: -0.0000

Data Index: 8635 (The Pile)

Max Activating Token Index: 266