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

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

Neuron 2822 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3646. Min Range: -3.3646

Max Act: 3.3646. Min Act: -0.0000

Data Index: 319882 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 3.3646. Min Range: -3.3646

Max Act: 3.0250. Min Act: -0.0000

Data Index: 601173 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.7083. Min Act: -0.0000

Data Index: 1331833 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.1355. Min Act: -0.0000

Data Index: 627605 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.6079. Min Act: -0.0000

Data Index: 752997 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.6167. Min Act: -0.0000

Data Index: 406104 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.5904. Min Act: -0.0000

Data Index: 311858 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.3975. Min Act: -0.0000

Data Index: 1371683 (Python Code)

Max Activating Token Index: 568

Text #8

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.3446. Min Act: -0.0000

Data Index: 693488 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.3267. Min Act: -0.0000

Data Index: 646707 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.2892. Min Act: -0.0000

Data Index: 1500726 (Python Code)

Max Activating Token Index: 485

Text #11

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.0971. Min Act: -0.0000

Data Index: 1089526 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.0935. Min Act: -0.0000

Data Index: 1509456 (Python Code)

Max Activating Token Index: 154

Text #13

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.1776. Min Act: -0.0000

Data Index: 1037668 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 3.3646. Min Range: -3.3646

Max Act: 2.0745. Min Act: -0.0000

Data Index: 432028 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 3.3646. Min Range: -3.3646

Max Act: 1.9491. Min Act: -0.0000

Data Index: 1518395 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 3.3646. Min Range: -3.3646

Max Act: 1.9307. Min Act: -0.0000

Data Index: 586765 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 3.3646. Min Range: -3.3646

Max Act: 1.9011. Min Act: -0.0000

Data Index: 215657 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 3.3646. Min Range: -3.3646

Max Act: 1.8644. Min Act: -0.0000

Data Index: 1313721 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 3.3646. Min Range: -3.3646

Max Act: 1.9461. Min Act: -0.0000

Data Index: 1601726 (Python Code)

Max Activating Token Index: 209