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

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

Neuron 5077 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3439. Min Range: -2.3439

Max Act: 2.3439. Min Act: -0.0000

Data Index: 649756 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 2.3439. Min Range: -2.3439

Max Act: 2.1163. Min Act: -0.0000

Data Index: 301234 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.9712. Min Act: -0.0000

Data Index: 931958 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.5924. Min Act: -0.0000

Data Index: 737980 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.5958. Min Act: -0.0000

Data Index: 877927 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1271133 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1245980 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.4061. Min Act: -0.0000

Data Index: 1111977 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.2895. Min Act: -0.0000

Data Index: 48765 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1238004 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.3328. Min Act: -0.0000

Data Index: 668865 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.3154. Min Act: -0.0000

Data Index: 1215739 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.3086. Min Act: -0.0000

Data Index: 61573 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.3038. Min Act: -0.0000

Data Index: 218724 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1017895 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.2841. Min Act: -0.0000

Data Index: 852788 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.2844. Min Act: -0.0000

Data Index: 606900 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.3487. Min Act: -0.0000

Data Index: 1167063 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.3110. Min Act: -0.0000

Data Index: 1062100 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 2.3439. Min Range: -2.3439

Max Act: 1.2242. Min Act: -0.0000

Data Index: 1205749 (C4 (Web Text))

Max Activating Token Index: 921