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

Dataset: The Pile

Neuron 3341 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: 0.3468. Min Range: -0.3468

Max Act: 0.3468. Min Act: -0.0000

Data Index: 639592 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1732803 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.3116. Min Act: -0.0000

Data Index: 616247 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.3143. Min Act: -0.0000

Data Index: 162326 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.3109. Min Act: -0.0000

Data Index: 458441 (The Pile)

Max Activating Token Index: 988

Text #5

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1744455 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1527371 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1875470 (The Pile)

Max Activating Token Index: 386

Text #8

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1557685 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.3083. Min Act: -0.0000

Data Index: 940942 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2836. Min Act: -0.0000

Data Index: 576591 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1460752 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.3018. Min Act: -0.0000

Data Index: 647086 (The Pile)

Max Activating Token Index: 483

Text #13

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1687531 (The Pile)

Max Activating Token Index: 195

Text #14

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1536384 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2792. Min Act: -0.0000

Data Index: 851541 (The Pile)

Max Activating Token Index: 528

Text #16

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2782. Min Act: -0.0000

Data Index: 566824 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2919. Min Act: -0.0000

Data Index: 558491 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1165451 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 0.3468. Min Range: -0.3468

Max Act: 0.2810. Min Act: -0.0000

Data Index: 398656 (The Pile)

Max Activating Token Index: 275