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

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

Neuron 5944 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: 2.4046. Min Range: -2.4046

Max Act: 2.4046. Min Act: -0.0002

Data Index: 1085295 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 2.4046. Min Range: -2.4046

Max Act: 2.1982. Min Act: -0.0002

Data Index: 1178142 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 2.4046. Min Range: -2.4046

Max Act: 2.0334. Min Act: -0.0002

Data Index: 1106271 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.9310. Min Act: -0.0002

Data Index: 632894 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.8787. Min Act: -0.0002

Data Index: 744353 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.8644. Min Act: -0.0002

Data Index: 409978 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.8487. Min Act: -0.0002

Data Index: 425572 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.8639. Min Act: -0.0003

Data Index: 1009974 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.7424. Min Act: -0.0002

Data Index: 925535 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.7777. Min Act: -0.0002

Data Index: 689899 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.7167. Min Act: -0.0002

Data Index: 246505 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.6772. Min Act: -0.0002

Data Index: 1128463 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.6745. Min Act: -0.0002

Data Index: 934146 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.6777. Min Act: -0.0002

Data Index: 411508 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.7073. Min Act: -0.0002

Data Index: 648013 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.6684. Min Act: -0.0002

Data Index: 47781 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.7110. Min Act: -0.0002

Data Index: 207908 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.6744. Min Act: -0.0002

Data Index: 54826 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.6683. Min Act: -0.0002

Data Index: 918175 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 2.4046. Min Range: -2.4046

Max Act: 1.6051. Min Act: -0.0002

Data Index: 1101898 (C4 (Web Text))

Max Activating Token Index: 348