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

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

Neuron 4211 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.2429. Min Act: -0.0000

Data Index: 1361949 (Python Code)

Max Activating Token Index: 827

Text #1

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.1268. Min Act: -0.0000

Data Index: 1449895 (Python Code)

Max Activating Token Index: 319

Text #2

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0547. Min Act: -0.0000

Data Index: 41285 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.9435. Min Act: -0.0000

Data Index: 421268 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.1130. Min Act: -0.0000

Data Index: 1631068 (Python Code)

Max Activating Token Index: 183

Text #5

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0311. Min Act: -0.0000

Data Index: 147013 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.1101. Min Act: -0.0000

Data Index: 424940 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.1125. Min Act: -0.0000

Data Index: 289352 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1442015 (Python Code)

Max Activating Token Index: 997

Text #9

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0728. Min Act: -0.0000

Data Index: 1641406 (Python Code)

Max Activating Token Index: 458

Text #10

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0773. Min Act: -0.0000

Data Index: 1552966 (Python Code)

Max Activating Token Index: 260

Text #11

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0737. Min Act: -0.0000

Data Index: 858273 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.1175. Min Act: -0.0000

Data Index: 1643074 (Python Code)

Max Activating Token Index: 873

Text #13

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0479. Min Act: -0.0000

Data Index: 309626 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0417. Min Act: -0.0000

Data Index: 280376 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.9752. Min Act: -0.0000

Data Index: 829677 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.9772. Min Act: -0.0000

Data Index: 442454 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1529193 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1409598 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.1551. Min Act: -0.0000

Data Index: 1464504 (Python Code)

Max Activating Token Index: 253