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

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

Neuron 600 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: 0.6628. Min Range: -0.6628

Max Act: 0.6248. Min Act: -0.0000

Data Index: 86710 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1057158 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5927. Min Act: -0.0000

Data Index: 521132 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4934. Min Act: -0.0000

Data Index: 972731 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4891. Min Act: -0.0000

Data Index: 360362 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4650. Min Act: -0.0000

Data Index: 824597 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4660. Min Act: -0.0000

Data Index: 4260 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1338590 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4342. Min Act: -0.0000

Data Index: 310651 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4019. Min Act: -0.0000

Data Index: 631210 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4829. Min Act: -0.0000

Data Index: 863383 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1122341 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1046707 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1009679 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1189995 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4272. Min Act: -0.0000

Data Index: 620493 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3964. Min Act: -0.0000

Data Index: 239343 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3926. Min Act: -0.0000

Data Index: 766177 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4015. Min Act: -0.0000

Data Index: 642934 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1356175 (C4 (Web Text))

Max Activating Token Index: 947