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

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

Neuron 2203 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: 1.6617. Min Range: -1.6617

Max Act: 1.6617. Min Act: -0.0002

Data Index: 1176040 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.5897. Min Act: -0.0002

Data Index: 834289 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.5488. Min Act: -0.0002

Data Index: 1521019 (Python Code)

Max Activating Token Index: 170

Text #3

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.5230. Min Act: -0.0002

Data Index: 1373783 (Python Code)

Max Activating Token Index: 791

Text #4

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4967. Min Act: -0.0002

Data Index: 1567469 (Python Code)

Max Activating Token Index: 151

Text #5

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4696. Min Act: -0.0002

Data Index: 464355 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4325. Min Act: -0.0003

Data Index: 938863 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.3949. Min Act: -0.0002

Data Index: 596113 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.3917. Min Act: -0.0002

Data Index: 778229 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4084. Min Act: -0.0002

Data Index: 1375916 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4189. Min Act: -0.0002

Data Index: 1290466 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4099. Min Act: -0.0002

Data Index: 1629005 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4419. Min Act: -0.0002

Data Index: 963775 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4325. Min Act: -0.0002

Data Index: 826605 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4187. Min Act: -0.0002

Data Index: 133247 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4518. Min Act: -0.0002

Data Index: 1648388 (Python Code)

Max Activating Token Index: 584

Text #16

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.3857. Min Act: -0.0002

Data Index: 617281 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.3886. Min Act: -0.0002

Data Index: 203849 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4305. Min Act: -0.0002

Data Index: 874636 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.3747. Min Act: -0.0002

Data Index: 1405807 (Python Code)

Max Activating Token Index: 695