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

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

Neuron 2995 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: 2.5741. Min Range: -2.5741

Max Act: 2.5741. Min Act: -0.0000

Data Index: 1610790 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 2.5741. Min Range: -2.5741

Max Act: 2.2530. Min Act: -0.0000

Data Index: 1557937 (Python Code)

Max Activating Token Index: 123

Text #2

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.9668. Min Act: -0.0000

Data Index: 1592232 (Python Code)

Max Activating Token Index: 497

Text #3

Max Range: 2.5741. Min Range: -2.5741

Max Act: 2.1237. Min Act: -0.0000

Data Index: 1418711 (Python Code)

Max Activating Token Index: 320

Text #4

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.9806. Min Act: -0.0000

Data Index: 1559572 (Python Code)

Max Activating Token Index: 186

Text #5

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.8973. Min Act: -0.0000

Data Index: 1583347 (Python Code)

Max Activating Token Index: 248

Text #6

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.7513. Min Act: -0.0000

Data Index: 1523907 (Python Code)

Max Activating Token Index: 462

Text #7

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.7398. Min Act: -0.0001

Data Index: 1515864 (Python Code)

Max Activating Token Index: 296

Text #8

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.8346. Min Act: -0.0001

Data Index: 1642631 (Python Code)

Max Activating Token Index: 996

Text #9

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.7128. Min Act: -0.0001

Data Index: 1414458 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.7159. Min Act: -0.0000

Data Index: 1513777 (Python Code)

Max Activating Token Index: 940

Text #11

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.6357. Min Act: -0.0001

Data Index: 1639123 (Python Code)

Max Activating Token Index: 593

Text #12

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.5884. Min Act: -0.0000

Data Index: 1370927 (Python Code)

Max Activating Token Index: 793

Text #13

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.7244. Min Act: -0.0000

Data Index: 1536023 (Python Code)

Max Activating Token Index: 882

Text #14

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.7311. Min Act: -0.0000

Data Index: 1606051 (Python Code)

Max Activating Token Index: 407

Text #15

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.5231. Min Act: -0.0000

Data Index: 1609459 (Python Code)

Max Activating Token Index: 632

Text #16

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1518243 (Python Code)

Max Activating Token Index: 356

Text #17

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.6250. Min Act: -0.0000

Data Index: 1483643 (Python Code)

Max Activating Token Index: 252

Text #18

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.7311. Min Act: -0.0000

Data Index: 1563125 (Python Code)

Max Activating Token Index: 651

Text #19

Max Range: 2.5741. Min Range: -2.5741

Max Act: 1.6202. Min Act: -0.0000

Data Index: 1563417 (Python Code)

Max Activating Token Index: 894