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

Dataset: The Pile

Neuron 2503 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: 0.9222. Min Range: -0.9222

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1750713 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.9074. Min Act: -0.0000

Data Index: 660036 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1428256 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8463. Min Act: -0.0000

Data Index: 494224 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1455934 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1268131 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8192. Min Act: -0.0000

Data Index: 380641 (The Pile)

Max Activating Token Index: 600

Text #7

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1758073 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8273. Min Act: -0.0000

Data Index: 821174 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1748213 (The Pile)

Max Activating Token Index: 289

Text #10

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1259187 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1229516 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1511955 (The Pile)

Max Activating Token Index: 514

Text #13

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1538706 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1574117 (The Pile)

Max Activating Token Index: 475

Text #15

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7926. Min Act: -0.0000

Data Index: 910269 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8133. Min Act: -0.0000

Data Index: 220326 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1782373 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7202. Min Act: -0.0000

Data Index: 292743 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1036782 (The Pile)

Max Activating Token Index: 972