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

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

Neuron 4102 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: 2.5988. Min Range: -2.5988

Max Act: 2.5988. Min Act: -0.0000

Data Index: 502657 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.3762. Min Act: -0.0000

Data Index: 53917 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.1582. Min Act: -0.0000

Data Index: 556404 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.0699. Min Act: -0.0000

Data Index: 1199688 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.9140. Min Act: -0.0000

Data Index: 958504 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.9646. Min Act: -0.0000

Data Index: 1513656 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.0569. Min Act: -0.0000

Data Index: 184505 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.7232. Min Act: -0.0000

Data Index: 62625 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.7796. Min Act: -0.0000

Data Index: 1292608 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1112934 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.5321. Min Act: -0.0000

Data Index: 526899 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.6339. Min Act: -0.0000

Data Index: 989002 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.6287. Min Act: -0.0000

Data Index: 348051 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.6150. Min Act: -0.0000

Data Index: 1345062 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.6294. Min Act: -0.0000

Data Index: 1310448 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1393887 (Python Code)

Max Activating Token Index: 647

Text #16

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.5963. Min Act: -0.0000

Data Index: 586360 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.5801. Min Act: -0.0000

Data Index: 1179719 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.5505. Min Act: -0.0000

Data Index: 1651809 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 2.5988. Min Range: -2.5988

Max Act: 1.5366. Min Act: -0.0000

Data Index: 226586 (C4 (Web Text))

Max Activating Token Index: 102