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

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

Neuron 280 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: 1.3424. Min Range: -1.3424

Max Act: 1.3424. Min Act: -0.0000

Data Index: 581527 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 1.3424. Min Range: -1.3424

Max Act: 1.2334. Min Act: -0.0000

Data Index: 265295 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 1.3424. Min Range: -1.3424

Max Act: 1.0559. Min Act: -0.0000

Data Index: 554354 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.3424. Min Range: -1.3424

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1562756 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 1.3424. Min Range: -1.3424

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1355115 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 1.3424. Min Range: -1.3424

Max Act: 1.0579. Min Act: -0.0000

Data Index: 104813 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.3424. Min Range: -1.3424

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1580275 (Python Code)

Max Activating Token Index: 621

Text #7

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.9356. Min Act: -0.0000

Data Index: 870185 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.9663. Min Act: -0.0000

Data Index: 176453 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1543776 (Python Code)

Max Activating Token Index: 147

Text #10

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1036786 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1324775 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.9144. Min Act: -0.0000

Data Index: 425191 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1487293 (Python Code)

Max Activating Token Index: 451

Text #14

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1491637 (Python Code)

Max Activating Token Index: 199

Text #15

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1002125 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1644887 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1389438 (Python Code)

Max Activating Token Index: 740

Text #18

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.9037. Min Act: -0.0000

Data Index: 339892 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 1.3424. Min Range: -1.3424

Max Act: 0.8609. Min Act: -0.0000

Data Index: 141216 (C4 (Web Text))

Max Activating Token Index: 377