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

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

Neuron 40 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: 2.9323. Min Range: -2.9323

Max Act: 2.9323. Min Act: -0.0000

Data Index: 1346027 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 2.9323. Min Range: -2.9323

Max Act: 2.4722. Min Act: -0.0000

Data Index: 281010 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 2.9323. Min Range: -2.9323

Max Act: 2.4547. Min Act: -0.0000

Data Index: 778373 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 2.9323. Min Range: -2.9323

Max Act: 2.4308. Min Act: -0.0000

Data Index: 1308676 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.8791. Min Act: -0.0000

Data Index: 153626 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 2.9323. Min Range: -2.9323

Max Act: 2.2668. Min Act: -0.0000

Data Index: 336804 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 2.9323. Min Range: -2.9323

Max Act: 2.0227. Min Act: -0.0000

Data Index: 540706 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.9002. Min Act: -0.0000

Data Index: 172721 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.9651. Min Act: -0.0000

Data Index: 575055 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.9328. Min Act: -0.0000

Data Index: 1290132 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.8233. Min Act: -0.0000

Data Index: 1308302 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.9155. Min Act: -0.0000

Data Index: 875408 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.9104. Min Act: -0.0000

Data Index: 710420 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.9022. Min Act: -0.0000

Data Index: 1023593 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.6794. Min Act: -0.0000

Data Index: 150942 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.8541. Min Act: -0.0000

Data Index: 1216595 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.7819. Min Act: -0.0000

Data Index: 209055 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.6662. Min Act: -0.0000

Data Index: 699141 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.5796. Min Act: -0.0000

Data Index: 1284736 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 2.9323. Min Range: -2.9323

Max Act: 1.7277. Min Act: -0.0000

Data Index: 922638 (C4 (Web Text))

Max Activating Token Index: 1012