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

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

Neuron 691 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: 0.7716. Min Range: -0.7716

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1574576 (Python Code)

Max Activating Token Index: 274

Text #1

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1588062 (Python Code)

Max Activating Token Index: 71

Text #2

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1237597 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1616925 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4338. Min Act: -0.0000

Data Index: 363451 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1619379 (Python Code)

Max Activating Token Index: 183

Text #6

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.3615. Min Act: -0.0000

Data Index: 39019 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.3425. Min Act: -0.0000

Data Index: 332502 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1347073 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1362777 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1489012 (Python Code)

Max Activating Token Index: 710

Text #11

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.3263. Min Act: -0.0000

Data Index: 227230 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.3356. Min Act: -0.0000

Data Index: 827028 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1604433 (Python Code)

Max Activating Token Index: 891

Text #14

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1299276 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1446891 (Python Code)

Max Activating Token Index: 398

Text #16

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1419894 (Python Code)

Max Activating Token Index: 978

Text #17

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1402806 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1363833 (Python Code)

Max Activating Token Index: 339

Text #19

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.2827. Min Act: -0.0000

Data Index: 334207 (C4 (Web Text))

Max Activating Token Index: 944