Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2717 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.7454. Min Act: -0.0001

Data Index: 997410 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.6685. Min Act: -0.0001

Data Index: 86742 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.6676. Min Act: -0.0001

Data Index: 711653 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5761. Min Act: -0.0001

Data Index: 444544 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5953. Min Act: -0.0001

Data Index: 857444 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5899. Min Act: -0.0001

Data Index: 676490 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5768. Min Act: -0.0001

Data Index: 706760 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5809. Min Act: -0.0001

Data Index: 434164 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5449. Min Act: -0.0001

Data Index: 49065 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5052. Min Act: -0.0001

Data Index: 983390 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5266. Min Act: -0.0001

Data Index: 967489 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5551. Min Act: -0.0001

Data Index: 593533 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5374. Min Act: -0.0001

Data Index: 485417 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5360. Min Act: -0.0001

Data Index: 1067170 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5116. Min Act: -0.0001

Data Index: 872568 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5304. Min Act: -0.0001

Data Index: 321612 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5218. Min Act: -0.0001

Data Index: 501111 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.4993. Min Act: -0.0001

Data Index: 649705 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.4780. Min Act: -0.0001

Data Index: 1012698 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5088. Min Act: -0.0001

Data Index: 982781 (C4 (Web Text))

Max Activating Token Index: 816