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

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

Neuron 136 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5962. Min Range: -6.5962

Max Act: 6.5702. Min Act: -0.0000

Data Index: 357398 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 6.5962. Min Range: -6.5962

Max Act: 6.5962. Min Act: -0.0000

Data Index: 149339 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 6.5962. Min Range: -6.5962

Max Act: 6.0575. Min Act: -0.0000

Data Index: 599970 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.8712. Min Act: -0.0000

Data Index: 995335 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 6.5962. Min Range: -6.5962

Max Act: 6.0569. Min Act: -0.0000

Data Index: 1332566 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 6.5962. Min Range: -6.5962

Max Act: 6.0530. Min Act: -0.0000

Data Index: 1211080 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.5869. Min Act: -0.0000

Data Index: 1229880 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.6770. Min Act: -0.0000

Data Index: 350996 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.4257. Min Act: -0.0000

Data Index: 854727 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.3942. Min Act: -0.0000

Data Index: 1646435 (Python Code)

Max Activating Token Index: 931

Text #10

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.6024. Min Act: -0.0000

Data Index: 1575695 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.6146. Min Act: -0.0000

Data Index: 1407471 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.0015. Min Act: -0.0000

Data Index: 1179269 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.2631. Min Act: -0.0000

Data Index: 1127203 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.5732. Min Act: -0.0000

Data Index: 1466918 (Python Code)

Max Activating Token Index: 518

Text #15

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.3500. Min Act: -0.0000

Data Index: 124950 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.2460. Min Act: -0.0000

Data Index: 1070824 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.1343. Min Act: -0.0000

Data Index: 479684 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.1110. Min Act: -0.0000

Data Index: 1404439 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 6.5962. Min Range: -6.5962

Max Act: 5.1380. Min Act: -0.0000

Data Index: 366590 (C4 (Web Text))

Max Activating Token Index: 850