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

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

Neuron 2566 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.3615. Min Act: -0.0000

Data Index: 1085135 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.4383. Min Act: -0.0000

Data Index: 157702 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.5943. Min Act: -0.0000

Data Index: 243209 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.5486. Min Act: -0.0000

Data Index: 556615 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.4357. Min Act: -0.0000

Data Index: 634213 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.4274. Min Act: -0.0000

Data Index: 820008 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.4290. Min Act: -0.0000

Data Index: 225260 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.5006. Min Act: -0.0000

Data Index: 534526 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.3635. Min Act: -0.0000

Data Index: 55969 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.4577. Min Act: -0.0000

Data Index: 1046152 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.3422. Min Act: -0.0000

Data Index: 226059 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.3450. Min Act: -0.0000

Data Index: 825474 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.4720. Min Act: -0.0000

Data Index: 1109559 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.4583. Min Act: -0.0000

Data Index: 849184 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.4475. Min Act: -0.0000

Data Index: 977958 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.4149. Min Act: -0.0000

Data Index: 582829 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.3096. Min Act: -0.0000

Data Index: 1122552 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.4389. Min Act: -0.0000

Data Index: 170445 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.3234. Min Act: -0.0000

Data Index: 676028 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 2.5943. Min Range: -2.5943

Max Act: 2.1674. Min Act: -0.0000

Data Index: 1092594 (C4 (Web Text))

Max Activating Token Index: 330