Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1232 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1198. Min Act: -0.0001

Data Index: 901604 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0965. Min Act: -0.0001

Data Index: 361466 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1425663 (Python Code)

Max Activating Token Index: 183

Text #3

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1508175 (Python Code)

Max Activating Token Index: 635

Text #4

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1363986 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1383661 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1414975 (Python Code)

Max Activating Token Index: 259

Text #7

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1553205 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1360657 (Python Code)

Max Activating Token Index: 146

Text #9

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1423103 (Python Code)

Max Activating Token Index: 172

Text #10

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0864. Min Act: -0.0001

Data Index: 45374 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0795. Min Act: -0.0001

Data Index: 321633 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1366739 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0837. Min Act: -0.0001

Data Index: 441004 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1575480 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0831. Min Act: -0.0001

Data Index: 463588 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1629357 (Python Code)

Max Activating Token Index: 754

Text #17

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0750. Min Act: -0.0001

Data Index: 321657 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1438000 (Python Code)

Max Activating Token Index: 189

Text #19

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1468561 (Python Code)

Max Activating Token Index: 12