Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3967 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9399. Min Act: -0.0001

Data Index: 1621876 (Python Code)

Max Activating Token Index: 722

Text #1

Max Range: 3.0282. Min Range: -3.0282

Max Act: 3.0282. Min Act: -0.0000

Data Index: 1564474 (Python Code)

Max Activating Token Index: 325

Text #2

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.6053. Min Act: -0.0000

Data Index: 1604363 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.8476. Min Act: -0.0001

Data Index: 1576738 (Python Code)

Max Activating Token Index: 405

Text #4

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9527. Min Act: -0.0001

Data Index: 1552824 (Python Code)

Max Activating Token Index: 137

Text #5

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.8124. Min Act: -0.0001

Data Index: 1438993 (Python Code)

Max Activating Token Index: 134

Text #6

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.6563. Min Act: -0.0001

Data Index: 1498655 (Python Code)

Max Activating Token Index: 216

Text #7

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.6041. Min Act: -0.0000

Data Index: 1495256 (Python Code)

Max Activating Token Index: 752

Text #8

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.7853. Min Act: -0.0001

Data Index: 1400190 (Python Code)

Max Activating Token Index: 512

Text #9

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.6487. Min Act: -0.0000

Data Index: 1375657 (Python Code)

Max Activating Token Index: 37

Text #10

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.4698. Min Act: -0.0001

Data Index: 1450564 (Python Code)

Max Activating Token Index: 977

Text #11

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.4521. Min Act: -0.0000

Data Index: 1586819 (Python Code)

Max Activating Token Index: 941

Text #12

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.5683. Min Act: -0.0001

Data Index: 1487133 (Python Code)

Max Activating Token Index: 806

Text #13

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.5657. Min Act: -0.0001

Data Index: 1574630 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.4289. Min Act: -0.0001

Data Index: 1643334 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.5268. Min Act: -0.0001

Data Index: 1592143 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.6636. Min Act: -0.0001

Data Index: 1378650 (Python Code)

Max Activating Token Index: 779

Text #17

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.5280. Min Act: -0.0001

Data Index: 1589965 (Python Code)

Max Activating Token Index: 57

Text #18

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.3026. Min Act: -0.0000

Data Index: 1510956 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.3832. Min Act: -0.0001

Data Index: 1447356 (Python Code)

Max Activating Token Index: 104