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

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

Neuron 2561 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.5457. Min Act: -0.0000

Data Index: 187100 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.5508. Min Act: -0.0000

Data Index: 203479 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2039. Min Act: -0.0000

Data Index: 96490 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.1912. Min Act: -0.0000

Data Index: 210083 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.1503. Min Act: -0.0000

Data Index: 886294 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.1294. Min Act: -0.0000

Data Index: 1063549 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.1092. Min Act: -0.0000

Data Index: 447423 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.1676. Min Act: -0.0000

Data Index: 311414 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.1430. Min Act: -0.0000

Data Index: 1153182 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1128165 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.1042. Min Act: -0.0000

Data Index: 931822 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.1546. Min Act: -0.0000

Data Index: 966859 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 1.5508. Min Range: -1.5508

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1030762 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.0347. Min Act: -0.0000

Data Index: 1079172 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 1.5508. Min Range: -1.5508

Max Act: 0.9774. Min Act: -0.0000

Data Index: 287263 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.0203. Min Act: -0.0000

Data Index: 649663 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1236755 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.0579. Min Act: -0.0000

Data Index: 459877 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.0581. Min Act: -0.0000

Data Index: 145428 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 1.5508. Min Range: -1.5508

Max Act: 0.9509. Min Act: -0.0000

Data Index: 486937 (C4 (Web Text))

Max Activating Token Index: 943