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

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

Neuron 4957 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: 3.7234. Min Range: -3.7234

Max Act: 3.5901. Min Act: -0.0000

Data Index: 158588 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.7234. Min Act: -0.0000

Data Index: 1354648 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.5105. Min Act: -0.0000

Data Index: 105502 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.3377. Min Act: -0.0000

Data Index: 1453086 (Python Code)

Max Activating Token Index: 904

Text #4

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.2577. Min Act: -0.0000

Data Index: 211119 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.1477. Min Act: -0.0000

Data Index: 901514 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.9308. Min Act: -0.0000

Data Index: 722303 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.0625. Min Act: -0.0000

Data Index: 1290121 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.8899. Min Act: -0.0000

Data Index: 308064 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.8845. Min Act: -0.0000

Data Index: 536498 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.6700. Min Act: -0.0000

Data Index: 800733 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.7981. Min Act: -0.0000

Data Index: 933150 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.7874. Min Act: -0.0000

Data Index: 887662 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.7778. Min Act: -0.0000

Data Index: 241292 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.6286. Min Act: -0.0000

Data Index: 1223937 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.7331. Min Act: -0.0000

Data Index: 589644 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.6306. Min Act: -0.0000

Data Index: 1204425 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.5678. Min Act: -0.0000

Data Index: 281932 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.7013. Min Act: -0.0000

Data Index: 203352 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.7020. Min Act: -0.0000

Data Index: 1300889 (C4 (Web Text))

Max Activating Token Index: 266