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

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

Neuron 3911 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1015172 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2859. Min Act: -0.0000

Data Index: 421449 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1317613 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2842. Min Act: -0.0000

Data Index: 405812 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2681. Min Act: -0.0000

Data Index: 522644 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2713. Min Act: -0.0000

Data Index: 919476 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2581. Min Act: -0.0000

Data Index: 441589 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1163965 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2889. Min Act: -0.0000

Data Index: 936214 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2804. Min Act: -0.0000

Data Index: 995108 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2463. Min Act: -0.0000

Data Index: 731382 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2636. Min Act: -0.0000

Data Index: 48746 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2424. Min Act: -0.0000

Data Index: 278826 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2381. Min Act: -0.0000

Data Index: 169148 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1303526 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2475. Min Act: -0.0000

Data Index: 835961 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2260. Min Act: -0.0000

Data Index: 754444 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2350. Min Act: -0.0000

Data Index: 48494 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2205. Min Act: -0.0000

Data Index: 500558 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2182. Min Act: -0.0000

Data Index: 641067 (C4 (Web Text))

Max Activating Token Index: 1015