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

Dataset: The Pile

Neuron 3722 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.3409. Min Act: -0.0000

Data Index: 1221470 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.3082. Min Act: -0.0000

Data Index: 520301 (The Pile)

Max Activating Token Index: 403

Text #2

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0923. Min Act: -0.0000

Data Index: 321514 (The Pile)

Max Activating Token Index: 319

Text #3

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0370. Min Act: -0.0000

Data Index: 1281521 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1861142 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1316611 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9920. Min Act: -0.0000

Data Index: 530666 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9848. Min Act: -0.0000

Data Index: 982599 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9974. Min Act: -0.0000

Data Index: 421499 (The Pile)

Max Activating Token Index: 255

Text #9

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9074. Min Act: -0.0000

Data Index: 384963 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1526180 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0220. Min Act: -0.0000

Data Index: 54253 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1735413 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9522. Min Act: -0.0000

Data Index: 774887 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9137. Min Act: -0.0000

Data Index: 813468 (The Pile)

Max Activating Token Index: 290

Text #15

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9364. Min Act: -0.0000

Data Index: 482140 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1556712 (The Pile)

Max Activating Token Index: 403

Text #17

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1370659 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1382818 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9716. Min Act: -0.0000

Data Index: 617618 (The Pile)

Max Activating Token Index: 110