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

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

Neuron 642 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0097. Min Range: -4.0097

Max Act: 4.0097. Min Act: -0.0000

Data Index: 650551 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 4.0097. Min Range: -4.0097

Max Act: 2.6022. Min Act: 0.0000

Data Index: 624352 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 4.0097. Min Range: -4.0097

Max Act: 2.5577. Min Act: 0.0000

Data Index: 1195494 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 4.0097. Min Range: -4.0097

Max Act: 2.3647. Min Act: -0.0000

Data Index: 1483804 (Python Code)

Max Activating Token Index: 959

Text #4

Max Range: 4.0097. Min Range: -4.0097

Max Act: 2.4780. Min Act: -0.0000

Data Index: 1502708 (Python Code)

Max Activating Token Index: 402

Text #5

Max Range: 4.0097. Min Range: -4.0097

Max Act: 2.1689. Min Act: -0.0000

Data Index: 723474 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.9927. Min Act: 0.0000

Data Index: 818057 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 4.0097. Min Range: -4.0097

Max Act: 2.0736. Min Act: -0.0000

Data Index: 448702 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.8576. Min Act: -0.0000

Data Index: 1099652 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.9479. Min Act: -0.0000

Data Index: 1343810 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.9110. Min Act: 0.0000

Data Index: 573022 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.7191. Min Act: 0.0001

Data Index: 1324271 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.7266. Min Act: -0.0000

Data Index: 1308164 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.7978. Min Act: -0.0000

Data Index: 222662 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.6816. Min Act: 0.0000

Data Index: 347928 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.6666. Min Act: -0.0000

Data Index: 1437641 (Python Code)

Max Activating Token Index: 792

Text #16

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.7652. Min Act: -0.0000

Data Index: 1034794 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.7404. Min Act: 0.0000

Data Index: 1284131 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.7440. Min Act: 0.0000

Data Index: 665673 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 4.0097. Min Range: -4.0097

Max Act: 1.6220. Min Act: 0.0001

Data Index: 793964 (C4 (Web Text))

Max Activating Token Index: 377