Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3869 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.3513. Min Act: -0.0000

Data Index: 281097 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.3614. Min Act: -0.0000

Data Index: 448901 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.2438. Min Act: -0.0000

Data Index: 258090 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0957. Min Act: -0.0000

Data Index: 810535 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0944. Min Act: -0.0000

Data Index: 548191 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0898. Min Act: -0.0000

Data Index: 23100 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0975. Min Act: -0.0000

Data Index: 79954 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0407. Min Act: -0.0001

Data Index: 1278797 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0448. Min Act: -0.0001

Data Index: 1051513 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0370. Min Act: -0.0001

Data Index: 1350273 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0102. Min Act: -0.0000

Data Index: 1198574 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0920. Min Act: -0.0001

Data Index: 961306 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0346. Min Act: -0.0000

Data Index: 557366 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0228. Min Act: -0.0001

Data Index: 307166 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0274. Min Act: -0.0000

Data Index: 71716 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.9964. Min Act: -0.0000

Data Index: 989471 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.9638. Min Act: -0.0001

Data Index: 697544 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0192. Min Act: -0.0000

Data Index: 413741 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0184. Min Act: -0.0000

Data Index: 455071 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0476. Min Act: -0.0000

Data Index: 130548 (C4 (Web Text))

Max Activating Token Index: 735