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

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

Neuron 1401 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.6626. Min Act: -0.0000

Data Index: 711367 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.1640. Min Act: -0.0000

Data Index: 1146095 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.4287. Min Act: -0.0000

Data Index: 649093 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.9859. Min Act: -0.0000

Data Index: 357424 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.0437. Min Act: -0.0000

Data Index: 708082 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.9091. Min Act: -0.0000

Data Index: 351130 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.5647. Min Act: -0.0000

Data Index: 731 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.6483. Min Act: -0.0000

Data Index: 865496 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.6693. Min Act: -0.0000

Data Index: 1052311 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.3606. Min Act: -0.0000

Data Index: 290737 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.2188. Min Act: -0.0000

Data Index: 271458 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.1344. Min Act: -0.0000

Data Index: 702524 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.0983. Min Act: -0.0000

Data Index: 712845 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.3142. Min Act: -0.0000

Data Index: 242551 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.0809. Min Act: -0.0000

Data Index: 1330766 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.2774. Min Act: -0.0000

Data Index: 419113 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.1669. Min Act: -0.0000

Data Index: 1146608 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.2932. Min Act: -0.0000

Data Index: 187347 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.0413. Min Act: -0.0000

Data Index: 841096 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 3.6626. Min Range: -3.6626

Max Act: 2.1481. Min Act: -0.0000

Data Index: 605455 (C4 (Web Text))

Max Activating Token Index: 39