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

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

Neuron 3923 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: 0.1324. Min Range: -0.1324

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1366642 (Python Code)

Max Activating Token Index: 653

Text #1

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1518406 (Python Code)

Max Activating Token Index: 595

Text #2

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1182. Min Act: -0.0002

Data Index: 425769 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1180. Min Act: -0.0002

Data Index: 958635 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1127. Min Act: -0.0002

Data Index: 528505 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1390005 (Python Code)

Max Activating Token Index: 554

Text #6

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1112. Min Act: -0.0002

Data Index: 479797 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1593334 (Python Code)

Max Activating Token Index: 578

Text #8

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1068. Min Act: -0.0002

Data Index: 1398533 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1438040 (Python Code)

Max Activating Token Index: 368

Text #10

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1599941 (Python Code)

Max Activating Token Index: 101

Text #11

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1481778 (Python Code)

Max Activating Token Index: 168

Text #12

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1426235 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1012. Min Act: -0.0002

Data Index: 1533853 (Python Code)

Max Activating Token Index: 969

Text #14

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1570746 (Python Code)

Max Activating Token Index: 347

Text #15

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1646144 (Python Code)

Max Activating Token Index: 877

Text #16

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1424542 (Python Code)

Max Activating Token Index: 480

Text #17

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1447363 (Python Code)

Max Activating Token Index: 563

Text #18

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1584915 (Python Code)

Max Activating Token Index: 116

Text #19

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1083678 (C4 (Web Text))

Max Activating Token Index: 160