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

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

Neuron 3784 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2561. Min Act: -0.0000

Data Index: 233183 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1855. Min Act: -0.0000

Data Index: 1355525 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1340. Min Act: -0.0000

Data Index: 330832 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1408. Min Act: -0.0000

Data Index: 181475 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1272. Min Act: -0.0000

Data Index: 141305 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1471. Min Act: -0.0000

Data Index: 570174 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1374346 (Python Code)

Max Activating Token Index: 381

Text #7

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1179. Min Act: -0.0000

Data Index: 802944 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1602714 (Python Code)

Max Activating Token Index: 157

Text #9

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1198. Min Act: -0.0000

Data Index: 5705 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1444466 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1231. Min Act: -0.0000

Data Index: 816646 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1181. Min Act: -0.0000

Data Index: 376521 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1209. Min Act: -0.0000

Data Index: 340169 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1597091 (Python Code)

Max Activating Token Index: 135

Text #15

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1162. Min Act: -0.0000

Data Index: 746358 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1527105 (Python Code)

Max Activating Token Index: 375

Text #17

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1641777 (Python Code)

Max Activating Token Index: 479

Text #18

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1050. Min Act: -0.0000

Data Index: 247313 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1403121 (Python Code)

Max Activating Token Index: 685