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

Dataset: The Pile

Neuron 5040 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3797. Min Act: -0.0000

Data Index: 834201 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1457756 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3632. Min Act: -0.0000

Data Index: 420489 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1756640 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1879895 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1998797 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1752872 (The Pile)

Max Activating Token Index: 813

Text #7

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1292483 (The Pile)

Max Activating Token Index: 374

Text #8

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2594. Min Act: -0.0000

Data Index: 17168 (The Pile)

Max Activating Token Index: 145

Text #9

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1657119 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1248057 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2507. Min Act: -0.0000

Data Index: 736978 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1214045 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1630305 (The Pile)

Max Activating Token Index: 165

Text #14

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1635191 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2437. Min Act: -0.0000

Data Index: 940454 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1330987 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2270. Min Act: 0.0000

Data Index: 785990 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2340. Min Act: -0.0000

Data Index: 109338 (The Pile)

Max Activating Token Index: 846

Text #19

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2248. Min Act: -0.0000

Data Index: 471252 (The Pile)

Max Activating Token Index: 886