Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3016 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.7557. Min Act: -0.0000

Data Index: 378132 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.3256. Min Act: -0.0000

Data Index: 533605 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.1447. Min Act: -0.0000

Data Index: 698306 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 2.7557. Min Range: -2.7557

Max Act: 1.9870. Min Act: -0.0000

Data Index: 1068326 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.1055. Min Act: -0.0000

Data Index: 62894 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.0757. Min Act: -0.0000

Data Index: 1052713 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.0642. Min Act: -0.0000

Data Index: 1031655 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.0504. Min Act: -0.0000

Data Index: 715160 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.0298. Min Act: -0.0000

Data Index: 604034 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 2.7557. Min Range: -2.7557

Max Act: 1.9024. Min Act: -0.0000

Data Index: 646250 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.0723. Min Act: -0.0000

Data Index: 230653 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 2.7557. Min Range: -2.7557

Max Act: 1.8997. Min Act: -0.0000

Data Index: 608404 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 2.7557. Min Range: -2.7557

Max Act: 1.9183. Min Act: -0.0000

Data Index: 21692 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 2.7557. Min Range: -2.7557

Max Act: 1.7980. Min Act: -0.0000

Data Index: 1307157 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 2.7557. Min Range: -2.7557

Max Act: 1.8991. Min Act: -0.0000

Data Index: 1181316 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 2.7557. Min Range: -2.7557

Max Act: 1.7833. Min Act: -0.0000

Data Index: 443074 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 2.7557. Min Range: -2.7557

Max Act: 1.8445. Min Act: -0.0000

Data Index: 648760 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 2.7557. Min Range: -2.7557

Max Act: 1.8333. Min Act: -0.0000

Data Index: 545446 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 2.7557. Min Range: -2.7557

Max Act: 1.8296. Min Act: -0.0000

Data Index: 945431 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 2.7557. Min Range: -2.7557

Max Act: 1.6889. Min Act: -0.0000

Data Index: 820638 (C4 (Web Text))

Max Activating Token Index: 693