Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2401 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1771384 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.5480. Min Act: -0.0000

Data Index: 441105 (The Pile)

Max Activating Token Index: 157

Text #2

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1485727 (The Pile)

Max Activating Token Index: 279

Text #3

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1842963 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1670153 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4945. Min Act: -0.0000

Data Index: 733625 (The Pile)

Max Activating Token Index: 906

Text #6

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1124205 (The Pile)

Max Activating Token Index: 997

Text #7

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1043088 (The Pile)

Max Activating Token Index: 285

Text #8

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.5024. Min Act: 0.0000

Data Index: 874202 (The Pile)

Max Activating Token Index: 965

Text #9

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4495. Min Act: -0.0001

Data Index: 191164 (The Pile)

Max Activating Token Index: 326

Text #10

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4141. Min Act: -0.0000

Data Index: 511052 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4987. Min Act: -0.0000

Data Index: 269854 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1935645 (The Pile)

Max Activating Token Index: 335

Text #13

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1776370 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1403398 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1393686 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4382. Min Act: -0.0000

Data Index: 442654 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4193. Min Act: -0.0000

Data Index: 411707 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4404. Min Act: -0.0000

Data Index: 680760 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1368614 (The Pile)

Max Activating Token Index: 589