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

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

Neuron 3925 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: 0.9276. Min Range: -0.9276

Max Act: 0.9276. Min Act: -0.0001

Data Index: 393410 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.8040. Min Act: -0.0000

Data Index: 140618 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1197485 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.6333. Min Act: -0.0000

Data Index: 897734 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.6262. Min Act: -0.0000

Data Index: 54912 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.6371. Min Act: -0.0000

Data Index: 46296 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5798. Min Act: -0.0000

Data Index: 185031 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1132458 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5234. Min Act: -0.0000

Data Index: 690315 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5457. Min Act: -0.0000

Data Index: 401224 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1279674 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5318. Min Act: -0.0000

Data Index: 58868 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5237. Min Act: -0.0000

Data Index: 381952 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5440. Min Act: -0.0000

Data Index: 608637 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1260945 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.4769. Min Act: -0.0001

Data Index: 127565 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5341. Min Act: -0.0000

Data Index: 670869 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.5072. Min Act: -0.0000

Data Index: 295119 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.4892. Min Act: -0.0001

Data Index: 1016503 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.9276. Min Range: -0.9276

Max Act: 0.4882. Min Act: -0.0000

Data Index: 900502 (C4 (Web Text))

Max Activating Token Index: 612