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

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

Neuron 2966 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1455217 (Python Code)

Max Activating Token Index: 1005

Text #1

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1497901 (Python Code)

Max Activating Token Index: 543

Text #2

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1429160 (Python Code)

Max Activating Token Index: 488

Text #3

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1202081 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1653433 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1647365 (Python Code)

Max Activating Token Index: 423

Text #6

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1583762 (Python Code)

Max Activating Token Index: 361

Text #7

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1604326 (Python Code)

Max Activating Token Index: 37

Text #8

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1553502 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1400017 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1595544 (Python Code)

Max Activating Token Index: 95

Text #11

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1415157 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1531753 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1375068 (Python Code)

Max Activating Token Index: 686

Text #14

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1417480 (Python Code)

Max Activating Token Index: 633

Text #15

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1591109 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1655140 (Python Code)

Max Activating Token Index: 664

Text #17

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1565226 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1647228 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1513165 (Python Code)

Max Activating Token Index: 271