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

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

Neuron 552 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1257. Min Range: -1.1257

Max Act: 1.1257. Min Act: -0.0001

Data Index: 63550 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.1257. Min Range: -1.1257

Max Act: 1.0188. Min Act: -0.0001

Data Index: 920680 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.8684. Min Act: -0.0001

Data Index: 523680 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.8597. Min Act: -0.0001

Data Index: 185966 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.8516. Min Act: -0.0000

Data Index: 894100 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.7889. Min Act: -0.0000

Data Index: 499561 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.7026. Min Act: -0.0001

Data Index: 1240265 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.7255. Min Act: -0.0001

Data Index: 1338082 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.8014. Min Act: -0.0001

Data Index: 502805 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.6932. Min Act: -0.0001

Data Index: 866599 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.7437. Min Act: -0.0001

Data Index: 1355655 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.7538. Min Act: -0.0001

Data Index: 843373 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.6956. Min Act: -0.0000

Data Index: 719834 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.6186. Min Act: -0.0001

Data Index: 299270 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.5352. Min Act: -0.0001

Data Index: 508872 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.6425. Min Act: -0.0000

Data Index: 148620 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.6361. Min Act: -0.0001

Data Index: 230528 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.6449. Min Act: -0.0001

Data Index: 1071459 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.6686. Min Act: -0.0001

Data Index: 1306816 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.6370. Min Act: -0.0001

Data Index: 52141 (C4 (Web Text))

Max Activating Token Index: 371