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

Dataset: The Pile

Neuron 2695 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: 5.1665. Min Range: -5.1665

Max Act: 5.1665. Min Act: -0.0000

Data Index: 1366550 (The Pile)

Max Activating Token Index: 32

Text #1

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.8916. Min Act: -0.0000

Data Index: 223342 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.6789. Min Act: -0.0000

Data Index: 1690657 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.8658. Min Act: -0.0000

Data Index: 1771833 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.6230. Min Act: -0.0000

Data Index: 729840 (The Pile)

Max Activating Token Index: 883

Text #5

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.5513. Min Act: -0.0000

Data Index: 361285 (The Pile)

Max Activating Token Index: 44

Text #6

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.1879. Min Act: -0.0000

Data Index: 861391 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.3100. Min Act: -0.0000

Data Index: 1991959 (The Pile)

Max Activating Token Index: 248

Text #8

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.5027. Min Act: -0.0000

Data Index: 1514928 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.5321. Min Act: -0.0000

Data Index: 514467 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.3016. Min Act: -0.0000

Data Index: 1988440 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.0647. Min Act: -0.0000

Data Index: 1861828 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.3133. Min Act: -0.0000

Data Index: 364026 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 5.1665. Min Range: -5.1665

Max Act: 3.9286. Min Act: -0.0000

Data Index: 438351 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.0826. Min Act: -0.0000

Data Index: 975194 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.0150. Min Act: -0.0000

Data Index: 1344419 (The Pile)

Max Activating Token Index: 137

Text #16

Max Range: 5.1665. Min Range: -5.1665

Max Act: 3.9696. Min Act: -0.0000

Data Index: 1518870 (The Pile)

Max Activating Token Index: 376

Text #17

Max Range: 5.1665. Min Range: -5.1665

Max Act: 3.9740. Min Act: -0.0000

Data Index: 1265190 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 5.1665. Min Range: -5.1665

Max Act: 3.7885. Min Act: -0.0000

Data Index: 1693592 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 5.1665. Min Range: -5.1665

Max Act: 3.9257. Min Act: -0.0000

Data Index: 978670 (The Pile)

Max Activating Token Index: 300