Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1465 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.4611. Min Act: -0.0002

Data Index: 442300 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.4833. Min Act: -0.0002

Data Index: 717298 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.4602. Min Act: -0.0002

Data Index: 1198721 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.4952. Min Act: -0.0002

Data Index: 304834 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.4297. Min Act: -0.0002

Data Index: 565916 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3993. Min Act: -0.0002

Data Index: 250238 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3612. Min Act: -0.0002

Data Index: 692028 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3964. Min Act: -0.0002

Data Index: 1001679 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3904. Min Act: -0.0002

Data Index: 1306822 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3912. Min Act: -0.0002

Data Index: 1285568 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.4182. Min Act: -0.0002

Data Index: 488234 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3866. Min Act: -0.0002

Data Index: 1227090 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3688. Min Act: -0.0002

Data Index: 1005202 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3686. Min Act: -0.0002

Data Index: 1032371 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3740. Min Act: -0.0002

Data Index: 924670 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3891. Min Act: -0.0002

Data Index: 894911 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3579. Min Act: -0.0002

Data Index: 215787 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3683. Min Act: -0.0002

Data Index: 91330 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3705. Min Act: -0.0002

Data Index: 90245 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3829. Min Act: -0.0002

Data Index: 311206 (C4 (Web Text))

Max Activating Token Index: 691