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

Dataset: The Pile

Neuron 191 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.7979. Min Act: -0.0000

Data Index: 1824890 (The Pile)

Max Activating Token Index: 886

Text #1

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.7339. Min Act: -0.0000

Data Index: 1735809 (The Pile)

Max Activating Token Index: 250

Text #2

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.4753. Min Act: -0.0000

Data Index: 124177 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.4981. Min Act: -0.0000

Data Index: 589026 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.5359. Min Act: -0.0000

Data Index: 465640 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1328300 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.4414. Min Act: -0.0000

Data Index: 353554 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.4301. Min Act: -0.0000

Data Index: 1741532 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.3395. Min Act: -0.0000

Data Index: 1603405 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.3783. Min Act: -0.0000

Data Index: 686206 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.4306. Min Act: -0.0000

Data Index: 12435 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.3025. Min Act: -0.0000

Data Index: 76805 (The Pile)

Max Activating Token Index: 139

Text #12

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.2381. Min Act: -0.0000

Data Index: 852901 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.2349. Min Act: -0.0000

Data Index: 746024 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.2204. Min Act: -0.0000

Data Index: 975886 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.2712. Min Act: -0.0000

Data Index: 143273 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.2090. Min Act: -0.0000

Data Index: 1935235 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.1910. Min Act: -0.0000

Data Index: 1835442 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1626829 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.3841. Min Act: -0.0000

Data Index: 1444233 (The Pile)

Max Activating Token Index: 920