Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4279 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2632. Min Act: -0.0000

Data Index: 163386 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1401969 (The Pile)

Max Activating Token Index: 202

Text #2

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1019127 (The Pile)

Max Activating Token Index: 535

Text #3

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2418. Min Act: -0.0000

Data Index: 43605 (The Pile)

Max Activating Token Index: 137

Text #4

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2320. Min Act: -0.0000

Data Index: 522422 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2269. Min Act: -0.0000

Data Index: 127350 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1275804 (The Pile)

Max Activating Token Index: 509

Text #7

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1770764 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1144931 (The Pile)

Max Activating Token Index: 474

Text #9

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2094. Min Act: -0.0000

Data Index: 361291 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2310. Min Act: -0.0000

Data Index: 339644 (The Pile)

Max Activating Token Index: 182

Text #11

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1442380 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2106. Min Act: -0.0000

Data Index: 698522 (The Pile)

Max Activating Token Index: 818

Text #13

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1813054 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2249. Min Act: -0.0000

Data Index: 710269 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2140. Min Act: -0.0000

Data Index: 847348 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1035326 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2110. Min Act: -0.0000

Data Index: 456423 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1886. Min Act: -0.0000

Data Index: 150244 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1942. Min Act: -0.0000

Data Index: 892506 (The Pile)

Max Activating Token Index: 716