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

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

Neuron 5237 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: 4.3682. Min Range: -4.3682

Max Act: 4.3682. Min Act: -0.0000

Data Index: 131721 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 4.3682. Min Range: -4.3682

Max Act: 4.1983. Min Act: -0.0000

Data Index: 249162 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.9100. Min Act: -0.0000

Data Index: 187743 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.8785. Min Act: -0.0000

Data Index: 1090995 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.6485. Min Act: -0.0000

Data Index: 93873 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.7752. Min Act: -0.0000

Data Index: 364385 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.2571. Min Act: -0.0001

Data Index: 305782 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.4157. Min Act: -0.0000

Data Index: 224837 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.4359. Min Act: -0.0000

Data Index: 1091922 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.1545. Min Act: -0.0000

Data Index: 367696 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.1437. Min Act: -0.0000

Data Index: 402745 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 4.3682. Min Range: -4.3682

Max Act: 2.9817. Min Act: -0.0000

Data Index: 1139217 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.2879. Min Act: -0.0000

Data Index: 374021 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.1280. Min Act: -0.0000

Data Index: 464016 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.1099. Min Act: -0.0000

Data Index: 1154187 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.2648. Min Act: -0.0000

Data Index: 206474 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.2576. Min Act: -0.0000

Data Index: 1124649 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.1590. Min Act: -0.0000

Data Index: 1151766 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.2684. Min Act: -0.0000

Data Index: 627188 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 4.3682. Min Range: -4.3682

Max Act: 3.1224. Min Act: -0.0000

Data Index: 963889 (C4 (Web Text))

Max Activating Token Index: 708