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

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

Neuron 575 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4947. Min Range: -2.4947

Max Act: 2.4947. Min Act: -0.0000

Data Index: 1222169 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 2.4947. Min Range: -2.4947

Max Act: 2.2147. Min Act: -0.0000

Data Index: 928142 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 2.4947. Min Range: -2.4947

Max Act: 2.0081. Min Act: -0.0000

Data Index: 1489959 (Python Code)

Max Activating Token Index: 251

Text #3

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.9439. Min Act: -0.0000

Data Index: 965103 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.8191. Min Act: -0.0000

Data Index: 63407 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 2.4947. Min Range: -2.4947

Max Act: 2.0470. Min Act: -0.0000

Data Index: 1078444 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.8709. Min Act: -0.0000

Data Index: 1187118 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.6630. Min Act: -0.0000

Data Index: 312008 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 2.4947. Min Range: -2.4947

Max Act: 2.0430. Min Act: -0.0000

Data Index: 841713 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.7114. Min Act: -0.0000

Data Index: 809930 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.6048. Min Act: -0.0000

Data Index: 602998 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.6662. Min Act: -0.0000

Data Index: 886640 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.5628. Min Act: -0.0000

Data Index: 1005253 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.6411. Min Act: -0.0000

Data Index: 1343666 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.7719. Min Act: -0.0000

Data Index: 921885 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.5086. Min Act: -0.0000

Data Index: 766970 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.6036. Min Act: -0.0000

Data Index: 504521 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.7540. Min Act: -0.0000

Data Index: 814059 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.5718. Min Act: -0.0000

Data Index: 1393396 (Python Code)

Max Activating Token Index: 581

Text #19

Max Range: 2.4947. Min Range: -2.4947

Max Act: 1.6219. Min Act: -0.0000

Data Index: 165131 (C4 (Web Text))

Max Activating Token Index: 727