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

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

Neuron 1365 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.1769. Min Act: -0.0001

Data Index: 193352 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.1039. Min Act: -0.0001

Data Index: 520057 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0576. Min Act: -0.0001

Data Index: 334081 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9437. Min Act: -0.0001

Data Index: 531918 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9991. Min Act: -0.0001

Data Index: 507793 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8886. Min Act: -0.0001

Data Index: 117034 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8054. Min Act: -0.0001

Data Index: 1057560 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8179. Min Act: -0.0001

Data Index: 1246603 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8393. Min Act: -0.0001

Data Index: 580790 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8168. Min Act: -0.0001

Data Index: 193932 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8109. Min Act: -0.0001

Data Index: 125987 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7667. Min Act: -0.0001

Data Index: 423410 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7265. Min Act: -0.0001

Data Index: 230531 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7628. Min Act: -0.0001

Data Index: 813793 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8384. Min Act: -0.0001

Data Index: 961458 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7781. Min Act: -0.0001

Data Index: 221368 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7313. Min Act: -0.0001

Data Index: 593436 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7494. Min Act: -0.0001

Data Index: 820792 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7349. Min Act: -0.0001

Data Index: 1049168 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6382. Min Act: -0.0001

Data Index: 248408 (C4 (Web Text))

Max Activating Token Index: 116