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

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

Neuron 4416 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.6194. Min Act: -0.0000

Data Index: 746533 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.4550. Min Act: -0.0000

Data Index: 135681 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.5637. Min Act: -0.0000

Data Index: 470642 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.3410. Min Act: -0.0000

Data Index: 21787 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.3649. Min Act: -0.0000

Data Index: 1057517 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.3398. Min Act: -0.0000

Data Index: 1231044 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.3283. Min Act: -0.0000

Data Index: 186618 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1087866 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.2818. Min Act: -0.0000

Data Index: 83111 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.2728. Min Act: -0.0000

Data Index: 871121 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.3234. Min Act: -0.0000

Data Index: 1334985 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1006488 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.2788. Min Act: -0.0000

Data Index: 994822 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.2368. Min Act: -0.0000

Data Index: 719183 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.2185. Min Act: -0.0000

Data Index: 1114046 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.2863. Min Act: -0.0000

Data Index: 1133022 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.1698. Min Act: -0.0000

Data Index: 726101 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.2256. Min Act: -0.0000

Data Index: 590036 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.1531. Min Act: -0.0000

Data Index: 1182478 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 1.6194. Min Range: -1.6194

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1081483 (C4 (Web Text))

Max Activating Token Index: 427