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

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

Neuron 2919 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: 0.2438. Min Range: -0.2438

Max Act: 0.2265. Min Act: -0.0001

Data Index: 977523 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.2038. Min Act: -0.0001

Data Index: 1161610 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.2156. Min Act: -0.0001

Data Index: 841624 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1929. Min Act: -0.0001

Data Index: 660971 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.2158. Min Act: -0.0001

Data Index: 34833 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.2438. Min Act: -0.0001

Data Index: 470800 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1047325 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1944. Min Act: -0.0001

Data Index: 49904 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1689. Min Act: -0.0001

Data Index: 193214 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.2326. Min Act: -0.0001

Data Index: 1176361 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1757. Min Act: -0.0001

Data Index: 151668 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1934. Min Act: -0.0001

Data Index: 539894 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1831. Min Act: -0.0001

Data Index: 942348 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1307597 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1862. Min Act: -0.0001

Data Index: 1065690 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1135714 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1825. Min Act: -0.0001

Data Index: 870548 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1645. Min Act: -0.0001

Data Index: 202560 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1696. Min Act: -0.0001

Data Index: 1143876 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1184046 (C4 (Web Text))

Max Activating Token Index: 78