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

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

Neuron 4852 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2413. Min Range: -3.2413

Max Act: 3.2413. Min Act: -0.0000

Data Index: 541345 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.5908. Min Act: -0.0000

Data Index: 689126 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.6948. Min Act: -0.0000

Data Index: 970186 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.4031. Min Act: -0.0000

Data Index: 480808 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.4897. Min Act: -0.0000

Data Index: 624312 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.3756. Min Act: -0.0000

Data Index: 413781 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.3539. Min Act: -0.0001

Data Index: 1206294 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.3283. Min Act: -0.0000

Data Index: 411586 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.1957. Min Act: -0.0000

Data Index: 1261269 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.1293. Min Act: -0.0000

Data Index: 1342089 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.0905. Min Act: -0.0000

Data Index: 426 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.0789. Min Act: -0.0000

Data Index: 462241 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 3.2413. Min Range: -3.2413

Max Act: 2.1867. Min Act: -0.0000

Data Index: 1332770 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 3.2413. Min Range: -3.2413

Max Act: 1.9108. Min Act: -0.0000

Data Index: 136338 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 3.2413. Min Range: -3.2413

Max Act: 1.9004. Min Act: -0.0000

Data Index: 502445 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 3.2413. Min Range: -3.2413

Max Act: 1.9178. Min Act: -0.0001

Data Index: 654003 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 3.2413. Min Range: -3.2413

Max Act: 1.7956. Min Act: -0.0000

Data Index: 1039232 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 3.2413. Min Range: -3.2413

Max Act: 1.7703. Min Act: -0.0000

Data Index: 551113 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 3.2413. Min Range: -3.2413

Max Act: 1.8534. Min Act: -0.0000

Data Index: 962249 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 3.2413. Min Range: -3.2413

Max Act: 1.6849. Min Act: -0.0001

Data Index: 491945 (C4 (Web Text))

Max Activating Token Index: 475