Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 707 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.5335. Min Act: -0.0001

Data Index: 1254449 (The Pile)

Max Activating Token Index: 934

Text #1

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4004. Min Act: -0.0001

Data Index: 1760583 (The Pile)

Max Activating Token Index: 593

Text #2

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3581. Min Act: -0.0000

Data Index: 940626 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3022. Min Act: -0.0000

Data Index: 611500 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3240. Min Act: -0.0001

Data Index: 1183395 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3028. Min Act: -0.0001

Data Index: 1574565 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1622948 (The Pile)

Max Activating Token Index: 897

Text #7

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3497. Min Act: -0.0001

Data Index: 1982943 (The Pile)

Max Activating Token Index: 67

Text #8

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1995548 (The Pile)

Max Activating Token Index: 405

Text #9

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3359. Min Act: -0.0000

Data Index: 578090 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2796. Min Act: -0.0001

Data Index: 1120432 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1249907 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2820. Min Act: -0.0000

Data Index: 521183 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2953. Min Act: -0.0000

Data Index: 431013 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2892. Min Act: -0.0001

Data Index: 1056909 (The Pile)

Max Activating Token Index: 397

Text #15

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2898. Min Act: -0.0001

Data Index: 589774 (The Pile)

Max Activating Token Index: 373

Text #16

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3084. Min Act: -0.0000

Data Index: 997013 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2796. Min Act: -0.0001

Data Index: 265405 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2612. Min Act: -0.0001

Data Index: 51729 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2909. Min Act: -0.0000

Data Index: 90167 (The Pile)

Max Activating Token Index: 928