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

Dataset: The Pile

Neuron 947 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1598213 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1840269 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.5693. Min Act: -0.0000

Data Index: 220203 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.5160. Min Act: -0.0001

Data Index: 1527783 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.5484. Min Act: -0.0000

Data Index: 399703 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4629. Min Act: -0.0000

Data Index: 736635 (The Pile)

Max Activating Token Index: 184

Text #6

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1647998 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4664. Min Act: -0.0000

Data Index: 841289 (The Pile)

Max Activating Token Index: 277

Text #8

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1829517 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1432805 (The Pile)

Max Activating Token Index: 173

Text #10

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1820523 (The Pile)

Max Activating Token Index: 888

Text #11

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1716362 (The Pile)

Max Activating Token Index: 861

Text #12

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4382. Min Act: -0.0000

Data Index: 954411 (The Pile)

Max Activating Token Index: 385

Text #13

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4507. Min Act: -0.0000

Data Index: 489844 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.3997. Min Act: -0.0000

Data Index: 530968 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4356. Min Act: -0.0000

Data Index: 332094 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4443. Min Act: -0.0000

Data Index: 136526 (The Pile)

Max Activating Token Index: 273

Text #17

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4299. Min Act: -0.0000

Data Index: 97465 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4371. Min Act: -0.0000

Data Index: 948736 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4077. Min Act: -0.0000

Data Index: 736531 (The Pile)

Max Activating Token Index: 176