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

Dataset: The Pile

Neuron 3181 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0433. Min Range: -7.0433

Max Act: 6.6210. Min Act: 0.0000

Data Index: 1511430 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 7.0433. Min Range: -7.0433

Max Act: 7.0433. Min Act: 0.0000

Data Index: 495585 (The Pile)

Max Activating Token Index: 535

Text #2

Max Range: 7.0433. Min Range: -7.0433

Max Act: 6.7700. Min Act: 0.0000

Data Index: 254862 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 7.0433. Min Range: -7.0433

Max Act: 6.0944. Min Act: 0.0000

Data Index: 766968 (The Pile)

Max Activating Token Index: 554

Text #4

Max Range: 7.0433. Min Range: -7.0433

Max Act: 6.0125. Min Act: -0.0000

Data Index: 1699108 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 7.0433. Min Range: -7.0433

Max Act: 5.6323. Min Act: -0.0000

Data Index: 8413 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 7.0433. Min Range: -7.0433

Max Act: 6.1791. Min Act: 0.0000

Data Index: 1620297 (The Pile)

Max Activating Token Index: 744

Text #7

Max Range: 7.0433. Min Range: -7.0433

Max Act: 5.4350. Min Act: 0.0000

Data Index: 102380 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 7.0433. Min Range: -7.0433

Max Act: 5.2765. Min Act: -0.0000

Data Index: 937024 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 7.0433. Min Range: -7.0433

Max Act: 5.4362. Min Act: 0.0000

Data Index: 404228 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 7.0433. Min Range: -7.0433

Max Act: 5.5120. Min Act: -0.0000

Data Index: 981758 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 7.0433. Min Range: -7.0433

Max Act: 5.1098. Min Act: -0.0000

Data Index: 297498 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 7.0433. Min Range: -7.0433

Max Act: 5.1617. Min Act: 0.0000

Data Index: 482263 (The Pile)

Max Activating Token Index: 281

Text #13

Max Range: 7.0433. Min Range: -7.0433

Max Act: 4.8707. Min Act: -0.0000

Data Index: 1625433 (The Pile)

Max Activating Token Index: 53

Text #14

Max Range: 7.0433. Min Range: -7.0433

Max Act: 4.6679. Min Act: 0.0000

Data Index: 344797 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 7.0433. Min Range: -7.0433

Max Act: 5.2652. Min Act: 0.0000

Data Index: 1621113 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 7.0433. Min Range: -7.0433

Max Act: 5.3963. Min Act: -0.0000

Data Index: 1369315 (The Pile)

Max Activating Token Index: 206

Text #17

Max Range: 7.0433. Min Range: -7.0433

Max Act: 4.8162. Min Act: -0.0000

Data Index: 1584668 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 7.0433. Min Range: -7.0433

Max Act: 4.6153. Min Act: -0.0000

Data Index: 825791 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 7.0433. Min Range: -7.0433

Max Act: 4.4891. Min Act: -0.0000

Data Index: 96534 (The Pile)

Max Activating Token Index: 192