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

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

Neuron 3675 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4142. Min Range: -1.4142

Max Act: 1.4142. Min Act: -0.0001

Data Index: 1415916 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 1.4142. Min Range: -1.4142

Max Act: 1.1823. Min Act: -0.0001

Data Index: 131251 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.4142. Min Range: -1.4142

Max Act: 1.1266. Min Act: -0.0001

Data Index: 1474439 (Python Code)

Max Activating Token Index: 792

Text #3

Max Range: 1.4142. Min Range: -1.4142

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1220643 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 1.4142. Min Range: -1.4142

Max Act: 1.1783. Min Act: -0.0001

Data Index: 1098269 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 1.4142. Min Range: -1.4142

Max Act: 1.0379. Min Act: -0.0001

Data Index: 1509566 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.9917. Min Act: -0.0001

Data Index: 1448416 (Python Code)

Max Activating Token Index: 933

Text #7

Max Range: 1.4142. Min Range: -1.4142

Max Act: 1.0435. Min Act: -0.0001

Data Index: 1414123 (Python Code)

Max Activating Token Index: 476

Text #8

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.9462. Min Act: -0.0001

Data Index: 372156 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1058966 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.8515. Min Act: -0.0000

Data Index: 16763 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 1.4142. Min Range: -1.4142

Max Act: 1.0846. Min Act: -0.0001

Data Index: 526760 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.9494. Min Act: -0.0001

Data Index: 1464302 (Python Code)

Max Activating Token Index: 901

Text #13

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.9524. Min Act: -0.0001

Data Index: 830409 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.9247. Min Act: -0.0001

Data Index: 1625412 (Python Code)

Max Activating Token Index: 948

Text #15

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.9797. Min Act: -0.0001

Data Index: 709946 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.8622. Min Act: -0.0001

Data Index: 1637184 (Python Code)

Max Activating Token Index: 181

Text #17

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.9055. Min Act: -0.0001

Data Index: 1599523 (Python Code)

Max Activating Token Index: 584

Text #18

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.9624. Min Act: -0.0001

Data Index: 238997 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 1.4142. Min Range: -1.4142

Max Act: 0.8914. Min Act: -0.0000

Data Index: 248821 (C4 (Web Text))

Max Activating Token Index: 849