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

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

Neuron 1686 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1622. Min Range: -1.1622

Max Act: 1.1449. Min Act: -0.0000

Data Index: 801043 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 1.1622. Min Range: -1.1622

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1264469 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 1.1622. Min Range: -1.1622

Max Act: 1.1458. Min Act: -0.0000

Data Index: 222094 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 1.1622. Min Range: -1.1622

Max Act: 1.0607. Min Act: -0.0000

Data Index: 387198 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9655. Min Act: -0.0000

Data Index: 683618 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9663. Min Act: -0.0000

Data Index: 929529 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9876. Min Act: -0.0000

Data Index: 794995 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8986. Min Act: -0.0000

Data Index: 518694 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9400. Min Act: -0.0000

Data Index: 223446 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8800. Min Act: -0.0000

Data Index: 244220 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9780. Min Act: -0.0000

Data Index: 628238 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8887. Min Act: -0.0000

Data Index: 368854 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8793. Min Act: -0.0000

Data Index: 556389 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9391. Min Act: -0.0000

Data Index: 96776 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8739. Min Act: -0.0000

Data Index: 99261 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8701. Min Act: -0.0000

Data Index: 268835 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8915. Min Act: -0.0000

Data Index: 1068731 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8955. Min Act: -0.0000

Data Index: 713018 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8593. Min Act: -0.0000

Data Index: 228137 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8561. Min Act: -0.0000

Data Index: 697531 (C4 (Web Text))

Max Activating Token Index: 113