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

Dataset: The Pile

Neuron 2156 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: 1.0964. Min Range: -1.0964

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1143845 (The Pile)

Max Activating Token Index: 292

Text #1

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1321732 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9400. Min Act: -0.0000

Data Index: 174038 (The Pile)

Max Activating Token Index: 175

Text #3

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1106962 (The Pile)

Max Activating Token Index: 664

Text #4

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9656. Min Act: -0.0000

Data Index: 117494 (The Pile)

Max Activating Token Index: 764

Text #5

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9660. Min Act: -0.0000

Data Index: 875123 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9612. Min Act: -0.0000

Data Index: 132642 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1202360 (The Pile)

Max Activating Token Index: 167

Text #8

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9358. Min Act: -0.0000

Data Index: 740410 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1793805 (The Pile)

Max Activating Token Index: 533

Text #10

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9277. Min Act: -0.0000

Data Index: 434284 (The Pile)

Max Activating Token Index: 10

Text #11

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9253. Min Act: -0.0000

Data Index: 198502 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1602922 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9687. Min Act: -0.0000

Data Index: 954076 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1218078 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8753. Min Act: -0.0000

Data Index: 373085 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8689. Min Act: -0.0000

Data Index: 273844 (The Pile)

Max Activating Token Index: 595

Text #17

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1256494 (The Pile)

Max Activating Token Index: 442

Text #18

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1823899 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1660949 (The Pile)

Max Activating Token Index: 499