Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 723 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.5930. Min Act: -0.0001

Data Index: 238432 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.6522. Min Act: -0.0000

Data Index: 598165 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.5379. Min Act: -0.0000

Data Index: 769517 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.6059. Min Act: -0.0001

Data Index: 575849 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.5096. Min Act: -0.0001

Data Index: 396140 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.5563. Min Act: -0.0000

Data Index: 517049 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.4132. Min Act: -0.0001

Data Index: 971837 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.5051. Min Act: -0.0000

Data Index: 383923 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.4164. Min Act: -0.0001

Data Index: 333438 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.4835. Min Act: -0.0000

Data Index: 870857 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.2846. Min Act: -0.0000

Data Index: 292647 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1040658 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.2996. Min Act: -0.0000

Data Index: 1103637 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.4018. Min Act: -0.0000

Data Index: 72488 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.4272. Min Act: -0.0001

Data Index: 104331 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.3903. Min Act: -0.0000

Data Index: 1197455 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.4834. Min Act: -0.0001

Data Index: 535355 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.3545. Min Act: -0.0000

Data Index: 905316 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.3138. Min Act: -0.0001

Data Index: 739458 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.3702. Min Act: -0.0000

Data Index: 765463 (C4 (Web Text))

Max Activating Token Index: 955