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

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

Neuron 4026 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.8603. Min Act: -0.0001

Data Index: 928014 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.8486. Min Act: -0.0001

Data Index: 1044906 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.8099. Min Act: -0.0001

Data Index: 1286362 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.8669. Min Act: -0.0001

Data Index: 1243081 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.8253. Min Act: -0.0001

Data Index: 1232728 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.7669. Min Act: -0.0001

Data Index: 390932 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.7115. Min Act: -0.0001

Data Index: 979652 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.6878. Min Act: -0.0001

Data Index: 1143355 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.7784. Min Act: -0.0001

Data Index: 860622 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.8007. Min Act: -0.0001

Data Index: 1314496 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.8228. Min Act: -0.0001

Data Index: 381773 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.6941. Min Act: -0.0001

Data Index: 689721 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.8035. Min Act: -0.0001

Data Index: 971909 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.7952. Min Act: -0.0001

Data Index: 1112832 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.7557. Min Act: -0.0001

Data Index: 301883 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.6784. Min Act: -0.0001

Data Index: 62363 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.6724. Min Act: -0.0001

Data Index: 41868 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.6703. Min Act: -0.0001

Data Index: 302682 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.7561. Min Act: -0.0001

Data Index: 1358349 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.7265. Min Act: -0.0001

Data Index: 427253 (C4 (Web Text))

Max Activating Token Index: 201