Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1781 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.6101. Min Act: -0.0000

Data Index: 141254 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.5972. Min Act: -0.0000

Data Index: 294065 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.7191. Min Act: -0.0000

Data Index: 800956 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.5894. Min Act: -0.0000

Data Index: 268063 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.4706. Min Act: -0.0000

Data Index: 705551 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.4570. Min Act: -0.0000

Data Index: 706570 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.4055. Min Act: -0.0000

Data Index: 731993 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.1301. Min Act: -0.0000

Data Index: 120031 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.3688. Min Act: -0.0000

Data Index: 315774 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.3726. Min Act: -0.0000

Data Index: 340779 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.3727. Min Act: -0.0000

Data Index: 285611 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.2969. Min Act: -0.0000

Data Index: 1307821 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.1888. Min Act: -0.0000

Data Index: 105333 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.1141. Min Act: -0.0000

Data Index: 843430 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.3060. Min Act: -0.0000

Data Index: 227396 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.3028. Min Act: -0.0000

Data Index: 1221018 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.3018. Min Act: -0.0000

Data Index: 646025 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.1772. Min Act: -0.0000

Data Index: 528185 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.2623. Min Act: -0.0000

Data Index: 1241542 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.2703. Min Act: -0.0000

Data Index: 1219379 (C4 (Web Text))

Max Activating Token Index: 37