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

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

Neuron 4402 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: 5.9136. Min Range: -5.9136

Max Act: 5.9136. Min Act: -0.0000

Data Index: 1596811 (Python Code)

Max Activating Token Index: 794

Text #1

Max Range: 5.9136. Min Range: -5.9136

Max Act: 5.0754. Min Act: -0.0000

Data Index: 859066 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 5.9136. Min Range: -5.9136

Max Act: 5.0044. Min Act: -0.0000

Data Index: 520274 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.4769. Min Act: -0.0000

Data Index: 1406058 (Python Code)

Max Activating Token Index: 424

Text #4

Max Range: 5.9136. Min Range: -5.9136

Max Act: 5.1874. Min Act: -0.0000

Data Index: 104493 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 5.9136. Min Range: -5.9136

Max Act: 5.0080. Min Act: -0.0000

Data Index: 642365 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.7806. Min Act: -0.0000

Data Index: 39816 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.3252. Min Act: -0.0000

Data Index: 1411961 (Python Code)

Max Activating Token Index: 643

Text #8

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.3061. Min Act: -0.0000

Data Index: 1377213 (Python Code)

Max Activating Token Index: 281

Text #9

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.6051. Min Act: -0.0000

Data Index: 702587 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.3373. Min Act: -0.0000

Data Index: 137022 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 5.9136. Min Range: -5.9136

Max Act: 3.9359. Min Act: -0.0000

Data Index: 887419 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.0873. Min Act: -0.0000

Data Index: 525436 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.2847. Min Act: -0.0000

Data Index: 1614096 (Python Code)

Max Activating Token Index: 622

Text #14

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.4585. Min Act: -0.0000

Data Index: 1514162 (Python Code)

Max Activating Token Index: 201

Text #15

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.0897. Min Act: -0.0000

Data Index: 1533743 (Python Code)

Max Activating Token Index: 438

Text #16

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.0861. Min Act: -0.0000

Data Index: 1582427 (Python Code)

Max Activating Token Index: 413

Text #17

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.2586. Min Act: -0.0000

Data Index: 1181500 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 5.9136. Min Range: -5.9136

Max Act: 4.0792. Min Act: -0.0000

Data Index: 1563922 (Python Code)

Max Activating Token Index: 346

Text #19

Max Range: 5.9136. Min Range: -5.9136

Max Act: 3.8730. Min Act: -0.0000

Data Index: 850763 (C4 (Web Text))

Max Activating Token Index: 21