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

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

Neuron 3280 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.4861. Min Act: -0.0000

Data Index: 399971 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.4079. Min Act: -0.0000

Data Index: 763801 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3998. Min Act: -0.0000

Data Index: 341294 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1318997 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.2657. Min Act: -0.0000

Data Index: 634226 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.2549. Min Act: -0.0000

Data Index: 857271 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.2475. Min Act: -0.0000

Data Index: 1105375 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.2666. Min Act: -0.0000

Data Index: 152611 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1142697 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.2608. Min Act: -0.0001

Data Index: 592064 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.2689. Min Act: -0.0000

Data Index: 156605 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.2780. Min Act: -0.0000

Data Index: 63547 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.1008. Min Act: -0.0000

Data Index: 3045 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.1264. Min Act: -0.0001

Data Index: 278046 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.1321. Min Act: -0.0000

Data Index: 1649855 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.0596. Min Act: -0.0001

Data Index: 676479 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1190100 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.0209. Min Act: -0.0000

Data Index: 327304 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.0346. Min Act: -0.0000

Data Index: 1584682 (Python Code)

Max Activating Token Index: 371

Text #19

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.0927. Min Act: -0.0001

Data Index: 1590627 (Python Code)

Max Activating Token Index: 935