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

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

Neuron 3858 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4562. Min Range: -2.4562

Max Act: 2.4562. Min Act: -0.0000

Data Index: 109216 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.8792. Min Act: -0.0000

Data Index: 1157748 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.7286. Min Act: -0.0000

Data Index: 712336 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.8342. Min Act: -0.0000

Data Index: 303606 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.6822. Min Act: -0.0000

Data Index: 1397388 (Python Code)

Max Activating Token Index: 873

Text #5

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.7534. Min Act: -0.0000

Data Index: 1291033 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.6421. Min Act: -0.0000

Data Index: 88246 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.4750. Min Act: -0.0000

Data Index: 557970 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.5254. Min Act: -0.0000

Data Index: 1285395 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.5190. Min Act: -0.0000

Data Index: 9598 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.5097. Min Act: -0.0000

Data Index: 1588322 (Python Code)

Max Activating Token Index: 751

Text #11

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.5053. Min Act: -0.0000

Data Index: 1655420 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.3999. Min Act: -0.0000

Data Index: 140258 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.4879. Min Act: -0.0000

Data Index: 663743 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.4524. Min Act: -0.0000

Data Index: 336459 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.4457. Min Act: -0.0000

Data Index: 232057 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.4351. Min Act: -0.0000

Data Index: 930001 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.3180. Min Act: -0.0000

Data Index: 605312 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1120121 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 2.4562. Min Range: -2.4562

Max Act: 1.2893. Min Act: -0.0000

Data Index: 986625 (C4 (Web Text))

Max Activating Token Index: 594