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

Dataset: The Pile

Neuron 166 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.6680. Min Act: -0.0000

Data Index: 19456 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1283267 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1266622 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1146985 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1857573 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1982085 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1346969 (The Pile)

Max Activating Token Index: 280

Text #7

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1040378 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5462. Min Act: -0.0000

Data Index: 218331 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.4901. Min Act: -0.0000

Data Index: 182666 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1797652 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5332. Min Act: -0.0000

Data Index: 967575 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1037234 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5194. Min Act: -0.0000

Data Index: 225964 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5115. Min Act: -0.0000

Data Index: 678320 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1211745 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5686. Min Act: -0.0000

Data Index: 179995 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1227242 (The Pile)

Max Activating Token Index: 432

Text #18

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5553. Min Act: -0.0000

Data Index: 416092 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1062665 (The Pile)

Max Activating Token Index: 661