Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3873 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.6497. Min Act: -0.0001

Data Index: 1011262 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5499. Min Act: -0.0001

Data Index: 514023 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5072. Min Act: -0.0002

Data Index: 1214217 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5054. Min Act: -0.0001

Data Index: 40042 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5090. Min Act: -0.0001

Data Index: 603419 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5049. Min Act: -0.0001

Data Index: 1231163 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5216. Min Act: -0.0001

Data Index: 448201 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5014. Min Act: -0.0001

Data Index: 1193298 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5153. Min Act: -0.0002

Data Index: 389842 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4808. Min Act: -0.0001

Data Index: 997074 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4887. Min Act: -0.0001

Data Index: 248211 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4902. Min Act: -0.0002

Data Index: 1178474 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5028. Min Act: -0.0002

Data Index: 1217286 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4744. Min Act: -0.0001

Data Index: 853336 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4815. Min Act: -0.0001

Data Index: 894502 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4820. Min Act: -0.0001

Data Index: 725613 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4780. Min Act: -0.0002

Data Index: 388395 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4800. Min Act: -0.0001

Data Index: 598049 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4794. Min Act: -0.0001

Data Index: 168237 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4755. Min Act: -0.0002

Data Index: 994155 (C4 (Web Text))

Max Activating Token Index: 678