Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2446 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.7359. Min Act: -0.0000

Data Index: 1073041 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.4969. Min Act: -0.0000

Data Index: 568128 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.1964. Min Act: -0.0000

Data Index: 216224 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.1770. Min Act: -0.0000

Data Index: 748886 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.1670. Min Act: -0.0000

Data Index: 686671 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.9724. Min Act: -0.0000

Data Index: 886619 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.9949. Min Act: -0.0000

Data Index: 341741 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.9310. Min Act: -0.0000

Data Index: 1194380 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.0022. Min Act: -0.0000

Data Index: 53922 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.8427. Min Act: -0.0000

Data Index: 425752 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.9859. Min Act: -0.0000

Data Index: 1169159 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.8033. Min Act: -0.0000

Data Index: 695500 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.6899. Min Act: -0.0000

Data Index: 764905 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.8201. Min Act: -0.0000

Data Index: 253659 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.8300. Min Act: -0.0000

Data Index: 611571 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.3690. Min Act: -0.0000

Data Index: 667029 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.1285. Min Act: -0.0000

Data Index: 245820 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.4211. Min Act: -0.0000

Data Index: 1266098 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.6651. Min Act: -0.0000

Data Index: 858941 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 4.7359. Min Range: -4.7359

Max Act: 3.2984. Min Act: -0.0000

Data Index: 1193717 (C4 (Web Text))

Max Activating Token Index: 350