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

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

Neuron 742 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0001

Data Index: 36493 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1524896 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0563. Min Act: -0.0001

Data Index: 208543 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0560. Min Act: -0.0001

Data Index: 472781 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0512. Min Act: -0.0001

Data Index: 459611 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0470. Min Act: -0.0001

Data Index: 885731 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0390. Min Act: -0.0001

Data Index: 128296 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1476530 (Python Code)

Max Activating Token Index: 396

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0416. Min Act: -0.0001

Data Index: 420552 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0486. Min Act: -0.0001

Data Index: 185676 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0449. Min Act: -0.0001

Data Index: 639346 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1298665 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0442. Min Act: -0.0001

Data Index: 1317711 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0444. Min Act: -0.0001

Data Index: 870167 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1153796 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0452. Min Act: -0.0001

Data Index: 325039 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0404. Min Act: -0.0001

Data Index: 853283 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0430. Min Act: -0.0001

Data Index: 62351 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0430. Min Act: -0.0001

Data Index: 424323 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1441226 (Python Code)

Max Activating Token Index: 77