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

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

Neuron 4175 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.2958. Min Act: -0.0000

Data Index: 1327675 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.1478. Min Act: -0.0000

Data Index: 575246 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1052488 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.0623. Min Act: -0.0000

Data Index: 379064 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.8844. Min Act: -0.0000

Data Index: 998099 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.8414. Min Act: -0.0000

Data Index: 487877 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.8067. Min Act: -0.0000

Data Index: 832953 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1084614 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7645. Min Act: -0.0000

Data Index: 742496 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1227930 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7437. Min Act: -0.0000

Data Index: 648253 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1212029 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7674. Min Act: -0.0000

Data Index: 290607 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7981. Min Act: -0.0000

Data Index: 12411 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1158623 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7617. Min Act: -0.0000

Data Index: 311269 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7773. Min Act: -0.0000

Data Index: 289661 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7453. Min Act: -0.0000

Data Index: 606772 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7189. Min Act: -0.0000

Data Index: 662112 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 1.2958. Min Range: -1.2958

Max Act: 0.7294. Min Act: -0.0000

Data Index: 667338 (C4 (Web Text))

Max Activating Token Index: 404