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

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

Neuron 200 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.8635. Min Act: -0.0000

Data Index: 1452154 (Python Code)

Max Activating Token Index: 748

Text #1

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.5789. Min Act: -0.0000

Data Index: 1366945 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.5588. Min Act: -0.0000

Data Index: 1627237 (Python Code)

Max Activating Token Index: 948

Text #3

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.5829. Min Act: -0.0000

Data Index: 1563852 (Python Code)

Max Activating Token Index: 737

Text #4

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.4476. Min Act: -0.0000

Data Index: 1587174 (Python Code)

Max Activating Token Index: 700

Text #5

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.5094. Min Act: -0.0000

Data Index: 1398237 (Python Code)

Max Activating Token Index: 869

Text #6

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.4538. Min Act: -0.0000

Data Index: 1400671 (Python Code)

Max Activating Token Index: 792

Text #7

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.4062. Min Act: -0.0000

Data Index: 1470882 (Python Code)

Max Activating Token Index: 552

Text #8

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.5416. Min Act: -0.0000

Data Index: 1472382 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.4020. Min Act: -0.0000

Data Index: 1486228 (Python Code)

Max Activating Token Index: 390

Text #10

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.3099. Min Act: -0.0000

Data Index: 1577825 (Python Code)

Max Activating Token Index: 212

Text #11

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.2046. Min Act: -0.0000

Data Index: 1601163 (Python Code)

Max Activating Token Index: 857

Text #12

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.3230. Min Act: -0.0000

Data Index: 1490961 (Python Code)

Max Activating Token Index: 321

Text #13

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.3244. Min Act: -0.0000

Data Index: 1575365 (Python Code)

Max Activating Token Index: 699

Text #14

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.3192. Min Act: -0.0000

Data Index: 1508002 (Python Code)

Max Activating Token Index: 269

Text #15

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.2930. Min Act: -0.0000

Data Index: 1568711 (Python Code)

Max Activating Token Index: 289

Text #16

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.4216. Min Act: -0.0000

Data Index: 1576347 (Python Code)

Max Activating Token Index: 1009

Text #17

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.2846. Min Act: -0.0000

Data Index: 1502294 (Python Code)

Max Activating Token Index: 639

Text #18

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.2961. Min Act: -0.0000

Data Index: 1653949 (Python Code)

Max Activating Token Index: 953

Text #19

Max Range: 2.8635. Min Range: -2.8635

Max Act: 2.3773. Min Act: -0.0000

Data Index: 1478070 (Python Code)

Max Activating Token Index: 1004