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

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

Neuron 1693 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.5574. Min Act: -0.0001

Data Index: 1351747 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.5173. Min Act: -0.0001

Data Index: 440407 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.5152. Min Act: -0.0001

Data Index: 63256 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.5034. Min Act: -0.0001

Data Index: 1325404 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4687. Min Act: -0.0001

Data Index: 639954 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4618. Min Act: -0.0001

Data Index: 237675 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.5084. Min Act: -0.0001

Data Index: 1210894 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4355. Min Act: -0.0001

Data Index: 996357 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4449. Min Act: -0.0001

Data Index: 727 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4882. Min Act: -0.0001

Data Index: 929627 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.5211. Min Act: -0.0001

Data Index: 1170127 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4646. Min Act: -0.0001

Data Index: 1141930 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4602. Min Act: -0.0001

Data Index: 682149 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4740. Min Act: -0.0001

Data Index: 516145 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4426. Min Act: -0.0001

Data Index: 61352 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4982. Min Act: -0.0001

Data Index: 666206 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4240. Min Act: -0.0001

Data Index: 1057464 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4325. Min Act: -0.0001

Data Index: 286226 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4497. Min Act: -0.0001

Data Index: 910048 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.5574. Min Range: -0.5574

Max Act: 0.4429. Min Act: -0.0001

Data Index: 492281 (C4 (Web Text))

Max Activating Token Index: 218