Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1386 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5976. Min Act: -0.0000

Data Index: 960702 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6662. Min Act: -0.0000

Data Index: 375373 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5142. Min Act: -0.0000

Data Index: 348921 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5364. Min Act: -0.0000

Data Index: 460830 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4754. Min Act: -0.0000

Data Index: 146347 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1214086 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5114. Min Act: -0.0000

Data Index: 832304 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4417. Min Act: -0.0000

Data Index: 416894 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4242. Min Act: -0.0000

Data Index: 5921 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4680. Min Act: -0.0000

Data Index: 898486 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4533. Min Act: -0.0000

Data Index: 766454 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1214127 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4411. Min Act: -0.0000

Data Index: 766008 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1352090 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.3996. Min Act: -0.0000

Data Index: 104570 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1499522 (Python Code)

Max Activating Token Index: 941

Text #16

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4537. Min Act: -0.0000

Data Index: 601260 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1652504 (Python Code)

Max Activating Token Index: 757

Text #18

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1462954 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1140401 (C4 (Web Text))

Max Activating Token Index: 93