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

Dataset: The Pile

Neuron 2930 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: 1.2451. Min Range: -1.2451

Max Act: 1.2451. Min Act: -0.0000

Data Index: 688453 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0617. Min Act: -0.0000

Data Index: 41031 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1114000 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1120592 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.9241. Min Act: -0.0000

Data Index: 1564370 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.8857. Min Act: -0.0000

Data Index: 343608 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1001691 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.8414. Min Act: -0.0000

Data Index: 713221 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1991707 (The Pile)

Max Activating Token Index: 397

Text #9

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1754876 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1976637 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1860988 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.7911. Min Act: -0.0000

Data Index: 362998 (The Pile)

Max Activating Token Index: 54

Text #13

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1060104 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.7561. Min Act: -0.0000

Data Index: 267847 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1018266 (The Pile)

Max Activating Token Index: 742

Text #16

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1104567 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.7918. Min Act: -0.0000

Data Index: 86047 (The Pile)

Max Activating Token Index: 670

Text #18

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1171178 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.7361. Min Act: -0.0000

Data Index: 129036 (The Pile)

Max Activating Token Index: 87