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

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

Neuron 5260 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: 1.8556. Min Range: -1.8556

Max Act: 1.8556. Min Act: -0.0002

Data Index: 186360 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.7297. Min Act: -0.0002

Data Index: 301636 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.6498. Min Act: -0.0002

Data Index: 1068769 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.6650. Min Act: -0.0002

Data Index: 29998 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.6208. Min Act: -0.0002

Data Index: 21991 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.6206. Min Act: -0.0002

Data Index: 643209 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5949. Min Act: -0.0002

Data Index: 349021 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.6305. Min Act: -0.0002

Data Index: 1024165 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.6305. Min Act: -0.0002

Data Index: 441233 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5923. Min Act: -0.0002

Data Index: 1220097 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5884. Min Act: -0.0002

Data Index: 357083 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5565. Min Act: -0.0002

Data Index: 1143659 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5682. Min Act: -0.0002

Data Index: 690656 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5543. Min Act: -0.0002

Data Index: 307579 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5338. Min Act: -0.0002

Data Index: 1183056 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5638. Min Act: -0.0002

Data Index: 423645 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5151. Min Act: -0.0002

Data Index: 89705 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5265. Min Act: -0.0002

Data Index: 1169441 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5064. Min Act: -0.0002

Data Index: 53179 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5508. Min Act: -0.0002

Data Index: 1073150 (C4 (Web Text))

Max Activating Token Index: 431