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

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

Neuron 4495 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2796. Min Act: -0.0001

Data Index: 26461 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2549. Min Act: -0.0001

Data Index: 1241366 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2125. Min Act: -0.0001

Data Index: 1173846 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.1059. Min Act: -0.0001

Data Index: 887254 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.0319. Min Act: -0.0001

Data Index: 1052272 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.8144. Min Act: -0.0001

Data Index: 129569 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.8260. Min Act: -0.0001

Data Index: 1298668 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.8198. Min Act: -0.0001

Data Index: 256261 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.3641. Min Act: -0.0001

Data Index: 1308775 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.5781. Min Act: -0.0001

Data Index: 481282 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.5602. Min Act: -0.0001

Data Index: 950065 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.6236. Min Act: -0.0001

Data Index: 553131 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 3.2796. Min Range: -3.2796

Max Act: 1.9745. Min Act: -0.0001

Data Index: 295931 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.8757. Min Act: -0.0001

Data Index: 1056351 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.6954. Min Act: -0.0001

Data Index: 586947 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.4615. Min Act: -0.0001

Data Index: 1015997 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.4319. Min Act: -0.0001

Data Index: 1245471 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.5532. Min Act: -0.0001

Data Index: 942007 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.4021. Min Act: -0.0001

Data Index: 644256 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 3.2796. Min Range: -3.2796

Max Act: 2.2905. Min Act: -0.0001

Data Index: 890624 (C4 (Web Text))

Max Activating Token Index: 856