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

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

Neuron 1820 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2200. Min Range: -4.2200

Max Act: 4.2200. Min Act: -0.0000

Data Index: 719652 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.5640. Min Act: -0.0000

Data Index: 664349 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.4079. Min Act: -0.0000

Data Index: 87915 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.2325. Min Act: -0.0000

Data Index: 106120 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.2381. Min Act: -0.0000

Data Index: 801161 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.4281. Min Act: -0.0000

Data Index: 4028 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.0695. Min Act: -0.0000

Data Index: 60097 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.5001. Min Act: -0.0000

Data Index: 868750 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.1923. Min Act: -0.0000

Data Index: 703503 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.1845. Min Act: -0.0000

Data Index: 1114745 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.1633. Min Act: -0.0000

Data Index: 618501 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.2719. Min Act: -0.0000

Data Index: 711912 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.2516. Min Act: -0.0000

Data Index: 810368 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.1282. Min Act: -0.0000

Data Index: 993645 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 4.2200. Min Range: -4.2200

Max Act: 2.8381. Min Act: -0.0000

Data Index: 1068843 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 4.2200. Min Range: -4.2200

Max Act: 2.5672. Min Act: -0.0000

Data Index: 1065592 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.0921. Min Act: -0.0000

Data Index: 697888 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 4.2200. Min Range: -4.2200

Max Act: 2.9219. Min Act: -0.0000

Data Index: 256666 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.3444. Min Act: -0.0000

Data Index: 765068 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 4.2200. Min Range: -4.2200

Max Act: 3.1561. Min Act: -0.0000

Data Index: 564255 (C4 (Web Text))

Max Activating Token Index: 285