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

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

Neuron 1028 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1002855 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1926. Min Act: -0.0001

Data Index: 560693 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1900. Min Act: -0.0001

Data Index: 872107 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1078445 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1845. Min Act: -0.0001

Data Index: 908759 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1413. Min Act: -0.0001

Data Index: 123275 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1931. Min Act: -0.0001

Data Index: 781471 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1679. Min Act: -0.0000

Data Index: 1566115 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1572. Min Act: -0.0000

Data Index: 868676 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1338044 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1491. Min Act: -0.0000

Data Index: 474021 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1553. Min Act: -0.0001

Data Index: 403371 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1605. Min Act: -0.0000

Data Index: 255163 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1641101 (Python Code)

Max Activating Token Index: 950

Text #14

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1147347 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1003016 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1141326 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1112214 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1541213 (Python Code)

Max Activating Token Index: 849

Text #19

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1047969 (C4 (Web Text))

Max Activating Token Index: 548