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

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

Neuron 3857 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: 2.5196. Min Range: -2.5196

Max Act: 2.5196. Min Act: -0.0000

Data Index: 1475707 (Python Code)

Max Activating Token Index: 771

Text #1

Max Range: 2.5196. Min Range: -2.5196

Max Act: 2.1932. Min Act: -0.0000

Data Index: 1609499 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 2.5196. Min Range: -2.5196

Max Act: 2.4166. Min Act: -0.0000

Data Index: 1611509 (Python Code)

Max Activating Token Index: 261

Text #3

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.9879. Min Act: -0.0000

Data Index: 1542289 (Python Code)

Max Activating Token Index: 590

Text #4

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.8448. Min Act: -0.0000

Data Index: 1409266 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.9233. Min Act: -0.0000

Data Index: 1605399 (Python Code)

Max Activating Token Index: 828

Text #6

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.7097. Min Act: -0.0000

Data Index: 1632243 (Python Code)

Max Activating Token Index: 670

Text #7

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.5161. Min Act: -0.0000

Data Index: 1408801 (Python Code)

Max Activating Token Index: 916

Text #8

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1370566 (Python Code)

Max Activating Token Index: 615

Text #9

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1477663 (Python Code)

Max Activating Token Index: 250

Text #10

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1471256 (Python Code)

Max Activating Token Index: 399

Text #11

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.3017. Min Act: -0.0000

Data Index: 1624857 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.2601. Min Act: -0.0000

Data Index: 1625553 (Python Code)

Max Activating Token Index: 628

Text #13

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.1886. Min Act: -0.0000

Data Index: 1379161 (Python Code)

Max Activating Token Index: 673

Text #14

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.1446. Min Act: -0.0000

Data Index: 1451672 (Python Code)

Max Activating Token Index: 144

Text #15

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1632388 (Python Code)

Max Activating Token Index: 161

Text #16

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.1503. Min Act: -0.0000

Data Index: 1653415 (Python Code)

Max Activating Token Index: 196

Text #17

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1600144 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1515756 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 2.5196. Min Range: -2.5196

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1590828 (Python Code)

Max Activating Token Index: 434