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

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

Neuron 5343 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: 0.1055. Min Range: -0.1055

Max Act: 0.1055. Min Act: -0.0002

Data Index: 1042844 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.1018. Min Act: -0.0002

Data Index: 612004 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.1007. Min Act: -0.0002

Data Index: 431495 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0964. Min Act: -0.0002

Data Index: 863326 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0979. Min Act: -0.0002

Data Index: 148441 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1053504 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0956. Min Act: -0.0002

Data Index: 721325 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0918. Min Act: -0.0002

Data Index: 983679 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0910. Min Act: -0.0002

Data Index: 707074 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1216854 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0901. Min Act: -0.0002

Data Index: 787925 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1013598 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0933. Min Act: -0.0002

Data Index: 639361 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1195565 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0933. Min Act: -0.0002

Data Index: 114292 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0933. Min Act: -0.0002

Data Index: 499373 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0915. Min Act: -0.0002

Data Index: 919077 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0909. Min Act: -0.0002

Data Index: 49146 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0922. Min Act: -0.0002

Data Index: 986542 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0902. Min Act: -0.0002

Data Index: 195669 (C4 (Web Text))

Max Activating Token Index: 32