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

Dataset: The Pile

Neuron 2691 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: 0.2649. Min Range: -0.2649

Max Act: 0.2649. Min Act: -0.0000

Data Index: 615829 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1137860 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2591. Min Act: -0.0000

Data Index: 631868 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2489. Min Act: -0.0000

Data Index: 215497 (The Pile)

Max Activating Token Index: 721

Text #4

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2368. Min Act: -0.0001

Data Index: 1599575 (The Pile)

Max Activating Token Index: 551

Text #5

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1230635 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1559808 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1325991 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1126717 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1283690 (The Pile)

Max Activating Token Index: 335

Text #10

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2267. Min Act: -0.0000

Data Index: 102668 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1721213 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2181. Min Act: -0.0000

Data Index: 466023 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1344320 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1806590 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2125. Min Act: -0.0000

Data Index: 769832 (The Pile)

Max Activating Token Index: 768

Text #16

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1980. Min Act: -0.0001

Data Index: 1205713 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2025. Min Act: -0.0000

Data Index: 193438 (The Pile)

Max Activating Token Index: 772

Text #18

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2101. Min Act: -0.0000

Data Index: 488915 (The Pile)

Max Activating Token Index: 318

Text #19

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2062. Min Act: -0.0000

Data Index: 11319 (The Pile)

Max Activating Token Index: 144