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

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

Neuron 1873 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4128. Min Range: -2.4128

Max Act: 2.4128. Min Act: -0.0001

Data Index: 1650484 (Python Code)

Max Activating Token Index: 198

Text #1

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.9998. Min Act: -0.0000

Data Index: 1614136 (Python Code)

Max Activating Token Index: 192

Text #2

Max Range: 2.4128. Min Range: -2.4128

Max Act: 2.2279. Min Act: -0.0000

Data Index: 1594328 (Python Code)

Max Activating Token Index: 87

Text #3

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.9952. Min Act: -0.0000

Data Index: 1531303 (Python Code)

Max Activating Token Index: 480

Text #4

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.9076. Min Act: -0.0000

Data Index: 1516093 (Python Code)

Max Activating Token Index: 687

Text #5

Max Range: 2.4128. Min Range: -2.4128

Max Act: 2.0252. Min Act: -0.0000

Data Index: 1493615 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.9001. Min Act: -0.0000

Data Index: 1635269 (Python Code)

Max Activating Token Index: 905

Text #7

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.8893. Min Act: -0.0000

Data Index: 1442648 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.7901. Min Act: -0.0000

Data Index: 1594172 (Python Code)

Max Activating Token Index: 528

Text #9

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.6569. Min Act: -0.0000

Data Index: 1393483 (Python Code)

Max Activating Token Index: 376

Text #10

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.6058. Min Act: -0.0000

Data Index: 1528488 (Python Code)

Max Activating Token Index: 977

Text #11

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.6880. Min Act: -0.0000

Data Index: 1154617 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.7762. Min Act: -0.0000

Data Index: 1372663 (Python Code)

Max Activating Token Index: 996

Text #13

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.4885. Min Act: -0.0000

Data Index: 30110 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.6481. Min Act: -0.0000

Data Index: 1420653 (Python Code)

Max Activating Token Index: 602

Text #15

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.6395. Min Act: -0.0000

Data Index: 1426716 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.6658. Min Act: -0.0000

Data Index: 1629704 (Python Code)

Max Activating Token Index: 225

Text #17

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1653856 (Python Code)

Max Activating Token Index: 171

Text #18

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.6158. Min Act: -0.0000

Data Index: 550649 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 2.4128. Min Range: -2.4128

Max Act: 1.7411. Min Act: -0.0000

Data Index: 1411673 (Python Code)

Max Activating Token Index: 716