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

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

Neuron 4403 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.4000. Min Act: -0.0000

Data Index: 754633 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.1737. Min Act: -0.0000

Data Index: 914218 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1296517 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.1872. Min Act: -0.0000

Data Index: 988273 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.0797. Min Act: -0.0000

Data Index: 1329518 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.0800. Min Act: -0.0000

Data Index: 733923 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.0684. Min Act: -0.0000

Data Index: 559420 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.9833. Min Act: -0.0000

Data Index: 31266 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.0570. Min Act: -0.0000

Data Index: 442022 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1139754 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.0101. Min Act: -0.0000

Data Index: 719793 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.9125. Min Act: -0.0000

Data Index: 575864 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8877. Min Act: -0.0000

Data Index: 911944 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.9020. Min Act: -0.0000

Data Index: 973206 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1050847 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8991. Min Act: -0.0000

Data Index: 511518 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8702. Min Act: -0.0000

Data Index: 988613 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1304729 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1180481 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.9188. Min Act: -0.0000

Data Index: 755610 (C4 (Web Text))

Max Activating Token Index: 511