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

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

Neuron 3609 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1629574 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1484160 (Python Code)

Max Activating Token Index: 639

Text #2

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1025. Min Act: -0.0002

Data Index: 987581 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1510251 (Python Code)

Max Activating Token Index: 686

Text #4

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1482235 (Python Code)

Max Activating Token Index: 800

Text #5

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0951. Min Act: -0.0002

Data Index: 615677 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0952. Min Act: -0.0002

Data Index: 800126 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0930. Min Act: -0.0002

Data Index: 307641 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0942. Min Act: -0.0002

Data Index: 918402 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0924. Min Act: -0.0002

Data Index: 943296 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1327546 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1297879 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0913. Min Act: -0.0002

Data Index: 701624 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1058369 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0872. Min Act: -0.0002

Data Index: 199010 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0862. Min Act: -0.0002

Data Index: 145724 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1488948 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1317026 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0865. Min Act: -0.0002

Data Index: 439465 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0851. Min Act: -0.0002

Data Index: 332581 (C4 (Web Text))

Max Activating Token Index: 427