Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 103 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0831. Min Range: -1.0831

Max Act: 1.0831. Min Act: -0.0000

Data Index: 299343 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1026635 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1593560 (Python Code)

Max Activating Token Index: 117

Text #3

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.8015. Min Act: -0.0000

Data Index: 26467 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1125573 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.7401. Min Act: 0.0000

Data Index: 1409239 (Python Code)

Max Activating Token Index: 204

Text #6

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.5911. Min Act: -0.0000

Data Index: 61806 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.5203. Min Act: -0.0000

Data Index: 927368 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1403176 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1585914 (Python Code)

Max Activating Token Index: 852

Text #10

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1218654 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1340958 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1510496 (Python Code)

Max Activating Token Index: 403

Text #13

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.4556. Min Act: -0.0000

Data Index: 359794 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1517033 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1615828 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1542718 (Python Code)

Max Activating Token Index: 232

Text #17

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1489372 (Python Code)

Max Activating Token Index: 472

Text #18

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1358442 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.4302. Min Act: -0.0000

Data Index: 846196 (C4 (Web Text))

Max Activating Token Index: 83