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

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

Neuron 1374 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.5429. Min Act: -0.0000

Data Index: 887592 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4300. Min Act: -0.0000

Data Index: 473023 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1535276 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4190. Min Act: -0.0000

Data Index: 768580 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4154. Min Act: -0.0000

Data Index: 510696 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1494005 (Python Code)

Max Activating Token Index: 539

Text #6

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3937. Min Act: -0.0000

Data Index: 111464 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1401765 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1076628 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3842. Min Act: -0.0000

Data Index: 123426 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1049349 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1457328 (Python Code)

Max Activating Token Index: 279

Text #12

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3572. Min Act: -0.0000

Data Index: 433912 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1495482 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3704. Min Act: -0.0000

Data Index: 67755 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3710. Min Act: -0.0000

Data Index: 782264 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1081984 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3578. Min Act: -0.0000

Data Index: 49091 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3818. Min Act: -0.0000

Data Index: 259191 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3511. Min Act: -0.0000

Data Index: 919465 (C4 (Web Text))

Max Activating Token Index: 160