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

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

Neuron 2020 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: 1.2831. Min Range: -1.2831

Max Act: 1.2831. Min Act: -0.0001

Data Index: 3155 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1174. Min Act: -0.0001

Data Index: 742867 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1641. Min Act: -0.0001

Data Index: 1078933 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.2112. Min Act: -0.0001

Data Index: 953217 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1100. Min Act: -0.0001

Data Index: 220314 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0355. Min Act: -0.0000

Data Index: 476274 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0030. Min Act: -0.0000

Data Index: 724948 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0185. Min Act: -0.0000

Data Index: 980209 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1340162 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0457. Min Act: -0.0000

Data Index: 753256 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9575. Min Act: -0.0001

Data Index: 951335 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9824. Min Act: -0.0001

Data Index: 845279 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9992. Min Act: -0.0001

Data Index: 1002814 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9429. Min Act: -0.0001

Data Index: 454206 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9568. Min Act: -0.0001

Data Index: 1123505 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9500. Min Act: -0.0001

Data Index: 994961 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9486. Min Act: -0.0001

Data Index: 1349317 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9175. Min Act: -0.0000

Data Index: 124181 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9106. Min Act: -0.0001

Data Index: 37626 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9347. Min Act: -0.0000

Data Index: 867630 (C4 (Web Text))

Max Activating Token Index: 581