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

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

Neuron 5782 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.7529. Min Act: -0.0000

Data Index: 348605 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.7413. Min Act: -0.0000

Data Index: 428692 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.3750. Min Act: -0.0000

Data Index: 311026 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.3358. Min Act: -0.0000

Data Index: 653708 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.4996. Min Act: 0.0001

Data Index: 633441 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6432. Min Act: -0.0000

Data Index: 510127 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.2688. Min Act: -0.0000

Data Index: 268811 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.3733. Min Act: -0.0000

Data Index: 34897 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.3386. Min Act: -0.0000

Data Index: 775096 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.2846. Min Act: -0.0000

Data Index: 1088178 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.2510. Min Act: -0.0000

Data Index: 1153620 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.2436. Min Act: -0.0000

Data Index: 1053831 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.2077. Min Act: -0.0000

Data Index: 282731 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.1880. Min Act: 0.0000

Data Index: 939910 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.0237. Min Act: -0.0000

Data Index: 1325338 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.1686. Min Act: -0.0000

Data Index: 219241 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.1471. Min Act: 0.0001

Data Index: 1296054 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.1832. Min Act: -0.0000

Data Index: 1195898 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.0013. Min Act: -0.0000

Data Index: 734428 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.1088. Min Act: 0.0001

Data Index: 767421 (C4 (Web Text))

Max Activating Token Index: 500