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

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

Neuron 3217 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: 2.2529. Min Range: -2.2529

Max Act: 2.2529. Min Act: -0.0000

Data Index: 1050036 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 2.2529. Min Range: -2.2529

Max Act: 2.1230. Min Act: -0.0000

Data Index: 412678 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.9691. Min Act: -0.0000

Data Index: 580371 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.9569. Min Act: -0.0000

Data Index: 1591012 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 2.2529. Min Range: -2.2529

Max Act: 2.0330. Min Act: -0.0000

Data Index: 90547 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 2.2529. Min Range: -2.2529

Max Act: 2.0016. Min Act: -0.0000

Data Index: 862291 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.9514. Min Act: -0.0000

Data Index: 601956 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.9642. Min Act: -0.0000

Data Index: 150118 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.6684. Min Act: -0.0000

Data Index: 1651341 (Python Code)

Max Activating Token Index: 512

Text #9

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.7405. Min Act: -0.0000

Data Index: 972699 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.6150. Min Act: -0.0000

Data Index: 489013 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.6092. Min Act: -0.0000

Data Index: 100035 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1358572 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.6749. Min Act: -0.0000

Data Index: 862470 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.5722. Min Act: -0.0000

Data Index: 585344 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.6449. Min Act: -0.0000

Data Index: 833394 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.6375. Min Act: -0.0000

Data Index: 998212 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.5405. Min Act: -0.0000

Data Index: 128283 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.7400. Min Act: -0.0000

Data Index: 810642 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 2.2529. Min Range: -2.2529

Max Act: 1.6298. Min Act: -0.0000

Data Index: 1141593 (C4 (Web Text))

Max Activating Token Index: 849