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

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

Neuron 352 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: 1.4834. Min Range: -1.4834

Max Act: 1.4834. Min Act: -0.0002

Data Index: 498683 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.4631. Min Act: -0.0002

Data Index: 546999 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.3965. Min Act: -0.0002

Data Index: 655852 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.3944. Min Act: -0.0002

Data Index: 282825 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.4128. Min Act: -0.0002

Data Index: 180098 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.4032. Min Act: -0.0002

Data Index: 79865 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.4239. Min Act: -0.0002

Data Index: 1132052 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.2917. Min Act: -0.0002

Data Index: 1040954 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.2886. Min Act: -0.0002

Data Index: 935000 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.3616. Min Act: -0.0002

Data Index: 790805 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.3015. Min Act: -0.0002

Data Index: 708381 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.3127. Min Act: -0.0002

Data Index: 1328924 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.2753. Min Act: -0.0002

Data Index: 364127 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.2957. Min Act: -0.0002

Data Index: 188594 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.3136. Min Act: -0.0002

Data Index: 1323281 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.2619. Min Act: -0.0002

Data Index: 787388 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.2728. Min Act: -0.0002

Data Index: 298993 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.2745. Min Act: -0.0002

Data Index: 524210 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.2113. Min Act: -0.0002

Data Index: 899180 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 1.4834. Min Range: -1.4834

Max Act: 1.2081. Min Act: -0.0002

Data Index: 361110 (C4 (Web Text))

Max Activating Token Index: 723