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

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

Neuron 2341 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: 0.5638. Min Range: -0.5638

Max Act: 0.5638. Min Act: -0.0001

Data Index: 171466 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5458. Min Act: -0.0001

Data Index: 789889 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5527. Min Act: -0.0001

Data Index: 303073 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5402. Min Act: -0.0001

Data Index: 334610 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5105. Min Act: -0.0001

Data Index: 782942 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5188. Min Act: -0.0001

Data Index: 835889 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5003. Min Act: -0.0001

Data Index: 173849 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5350. Min Act: -0.0001

Data Index: 727913 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4942. Min Act: -0.0001

Data Index: 253645 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4956. Min Act: -0.0001

Data Index: 227469 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4803. Min Act: -0.0001

Data Index: 1069844 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4702. Min Act: -0.0001

Data Index: 903723 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4876. Min Act: -0.0001

Data Index: 842106 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4656. Min Act: -0.0001

Data Index: 314368 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4826. Min Act: -0.0001

Data Index: 167992 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4802. Min Act: -0.0001

Data Index: 837919 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4732. Min Act: -0.0001

Data Index: 935701 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4750. Min Act: -0.0001

Data Index: 266155 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4509. Min Act: -0.0001

Data Index: 943391 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4947. Min Act: -0.0001

Data Index: 1106037 (C4 (Web Text))

Max Activating Token Index: 830