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

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

Neuron 1260 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3447. Min Range: -3.3447

Max Act: 3.3447. Min Act: -0.0001

Data Index: 1614465 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 3.3447. Min Range: -3.3447

Max Act: 3.1706. Min Act: -0.0001

Data Index: 1445736 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 3.3447. Min Range: -3.3447

Max Act: 3.2336. Min Act: -0.0001

Data Index: 1511128 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 3.3447. Min Range: -3.3447

Max Act: 3.1383. Min Act: -0.0001

Data Index: 1517743 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.9047. Min Act: -0.0001

Data Index: 1477935 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.7589. Min Act: -0.0001

Data Index: 1643030 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.7589. Min Act: -0.0001

Data Index: 1606448 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.7589. Min Act: -0.0001

Data Index: 1398735 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.8527. Min Act: -0.0001

Data Index: 1610503 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.6584. Min Act: -0.0001

Data Index: 1545293 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.6390. Min Act: -0.0001

Data Index: 1491092 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.7409. Min Act: -0.0001

Data Index: 1626913 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.5202. Min Act: -0.0001

Data Index: 1575231 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.5033. Min Act: -0.0001

Data Index: 1452291 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.7268. Min Act: -0.0001

Data Index: 1555600 (Python Code)

Max Activating Token Index: 218

Text #15

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.4467. Min Act: -0.0001

Data Index: 1437592 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.3348. Min Act: -0.0001

Data Index: 1414676 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.3077. Min Act: -0.0001

Data Index: 1484243 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.3325. Min Act: -0.0001

Data Index: 1390726 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 3.3447. Min Range: -3.3447

Max Act: 2.2122. Min Act: -0.0001

Data Index: 1427791 (Python Code)

Max Activating Token Index: 7