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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3315 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1480. Min Range: -3.1480

Max Act: 3.1480. Min Act: -0.0000

Data Index: 800859 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.8571. Min Act: -0.0000

Data Index: 13912 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.6542. Min Act: -0.0000

Data Index: 216618 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.7479. Min Act: -0.0000

Data Index: 1075684 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.6689. Min Act: -0.0000

Data Index: 850602 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.6654. Min Act: -0.0000

Data Index: 1351835 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.6798. Min Act: -0.0000

Data Index: 186779 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.6477. Min Act: -0.0000

Data Index: 368297 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.6383. Min Act: -0.0000

Data Index: 346091 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.4736. Min Act: -0.0000

Data Index: 484185 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.5623. Min Act: -0.0000

Data Index: 717114 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.5446. Min Act: -0.0000

Data Index: 434227 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.5245. Min Act: -0.0000

Data Index: 1101300 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.4932. Min Act: 0.0000

Data Index: 853378 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.3435. Min Act: 0.0000

Data Index: 735554 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.4671. Min Act: -0.0000

Data Index: 1239679 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.3562. Min Act: -0.0000

Data Index: 48422 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.4586. Min Act: -0.0000

Data Index: 1149258 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.3067. Min Act: -0.0000

Data Index: 513143 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 3.1480. Min Range: -3.1480

Max Act: 2.4174. Min Act: -0.0000

Data Index: 1297062 (C4 (Web Text))

Max Activating Token Index: 554