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

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

Neuron 5872 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: 0.7978. Min Range: -0.7978

Max Act: 0.7978. Min Act: -0.0001

Data Index: 437735 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5549. Min Act: -0.0000

Data Index: 402316 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5667. Min Act: -0.0001

Data Index: 1287630 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5638. Min Act: -0.0001

Data Index: 821462 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4936. Min Act: -0.0000

Data Index: 987806 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4971. Min Act: -0.0000

Data Index: 110461 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4965. Min Act: -0.0001

Data Index: 385740 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4872. Min Act: -0.0001

Data Index: 689473 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5080. Min Act: -0.0001

Data Index: 180503 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4671. Min Act: -0.0001

Data Index: 141575 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4840. Min Act: -0.0001

Data Index: 531634 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4520. Min Act: -0.0001

Data Index: 1330870 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.3574. Min Act: -0.0001

Data Index: 1242083 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4007. Min Act: -0.0001

Data Index: 704864 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4101. Min Act: -0.0001

Data Index: 591876 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4215. Min Act: -0.0001

Data Index: 408710 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4209. Min Act: -0.0001

Data Index: 106200 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.3916. Min Act: -0.0001

Data Index: 84806 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.3821. Min Act: -0.0000

Data Index: 428791 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.4030. Min Act: -0.0001

Data Index: 544291 (C4 (Web Text))

Max Activating Token Index: 1022