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

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

Neuron 3963 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: 0.1188. Min Range: -0.1188

Max Act: 0.1188. Min Act: -0.0002

Data Index: 648222 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1047. Min Act: -0.0002

Data Index: 613335 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1037549 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0956. Min Act: -0.0002

Data Index: 191541 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1293190 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0927. Min Act: -0.0002

Data Index: 13837 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0907. Min Act: -0.0002

Data Index: 635892 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0861. Min Act: -0.0002

Data Index: 822683 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1174079 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0846. Min Act: -0.0002

Data Index: 602430 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1366057 (Python Code)

Max Activating Token Index: 753

Text #11

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0811. Min Act: -0.0002

Data Index: 282512 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0809. Min Act: -0.0002

Data Index: 811379 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1596749 (Python Code)

Max Activating Token Index: 198

Text #14

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0814. Min Act: -0.0002

Data Index: 53181 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0818. Min Act: -0.0002

Data Index: 674148 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1266495 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0798. Min Act: -0.0002

Data Index: 778383 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0798. Min Act: -0.0003

Data Index: 1264226 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0783. Min Act: -0.0002

Data Index: 897766 (C4 (Web Text))

Max Activating Token Index: 17