Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2011 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.6635. Min Act: -0.0001

Data Index: 1282615 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.5467. Min Act: -0.0001

Data Index: 205595 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4521. Min Act: -0.0001

Data Index: 152874 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4797. Min Act: -0.0001

Data Index: 9108 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4071. Min Act: -0.0001

Data Index: 1023613 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.3205. Min Act: -0.0001

Data Index: 506376 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4257. Min Act: -0.0001

Data Index: 73921 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.4447. Min Act: -0.0001

Data Index: 706274 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.2914. Min Act: -0.0001

Data Index: 147347 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.2536. Min Act: -0.0001

Data Index: 718866 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.0755. Min Act: -0.0001

Data Index: 171425 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.3502. Min Act: 0.0002

Data Index: 203208 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.2240. Min Act: -0.0001

Data Index: 1128678 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1567. Min Act: -0.0001

Data Index: 1074186 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1402. Min Act: -0.0001

Data Index: 1247985 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.2732. Min Act: -0.0001

Data Index: 249263 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.2574. Min Act: -0.0001

Data Index: 686320 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1314. Min Act: -0.0001

Data Index: 693844 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1356. Min Act: -0.0001

Data Index: 451171 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 1.6635. Min Range: -1.6635

Max Act: 1.1556. Min Act: -0.0001

Data Index: 994920 (C4 (Web Text))

Max Activating Token Index: 562