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

Dataset: The Pile

Neuron 141 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5846. Min Act: -0.0000

Data Index: 520496 (The Pile)

Max Activating Token Index: 323

Text #1

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1362501 (The Pile)

Max Activating Token Index: 705

Text #2

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1300212 (The Pile)

Max Activating Token Index: 487

Text #3

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1859458 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5135. Min Act: -0.0000

Data Index: 558495 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1775029 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4696. Min Act: -0.0000

Data Index: 303518 (The Pile)

Max Activating Token Index: 701

Text #7

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1259570 (The Pile)

Max Activating Token Index: 334

Text #8

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5450. Min Act: -0.0000

Data Index: 236970 (The Pile)

Max Activating Token Index: 789

Text #9

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4466. Min Act: -0.0000

Data Index: 216052 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1201812 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1483183 (The Pile)

Max Activating Token Index: 222

Text #12

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5065. Min Act: -0.0000

Data Index: 701738 (The Pile)

Max Activating Token Index: 380

Text #13

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1658250 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5084. Min Act: -0.0000

Data Index: 858212 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4684. Min Act: -0.0000

Data Index: 689898 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1287680 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4311. Min Act: -0.0000

Data Index: 483494 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4509. Min Act: -0.0000

Data Index: 445134 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1813667 (The Pile)

Max Activating Token Index: 135