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

Dataset: The Pile

Neuron 1286 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: 1.3385. Min Range: -1.3385

Max Act: 1.3385. Min Act: -0.0000

Data Index: 383738 (The Pile)

Max Activating Token Index: 292

Text #1

Max Range: 1.3385. Min Range: -1.3385

Max Act: 1.0173. Min Act: -0.0000

Data Index: 268901 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9837. Min Act: -0.0000

Data Index: 883134 (The Pile)

Max Activating Token Index: 149

Text #3

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1948027 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9314. Min Act: -0.0000

Data Index: 491491 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9252. Min Act: -0.0000

Data Index: 279114 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1389793 (The Pile)

Max Activating Token Index: 177

Text #7

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8879. Min Act: -0.0000

Data Index: 285000 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9092. Min Act: -0.0000

Data Index: 842341 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1475641 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9156. Min Act: -0.0000

Data Index: 48003 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8869. Min Act: -0.0000

Data Index: 728449 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1594301 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1317186 (The Pile)

Max Activating Token Index: 532

Text #14

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8701. Min Act: -0.0000

Data Index: 516931 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1954268 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1368123 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1554886 (The Pile)

Max Activating Token Index: 261

Text #18

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8868. Min Act: -0.0000

Data Index: 527559 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8391. Min Act: -0.0000

Data Index: 594000 (The Pile)

Max Activating Token Index: 824