Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3608 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0938. Min Range: -1.0938

Max Act: 1.0938. Min Act: -0.0000

Data Index: 251587 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9682. Min Act: -0.0000

Data Index: 925514 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9661. Min Act: -0.0000

Data Index: 726501 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 1.0938. Min Range: -1.0938

Max Act: 1.0154. Min Act: -0.0001

Data Index: 672580 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9457. Min Act: -0.0000

Data Index: 291803 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9737. Min Act: -0.0001

Data Index: 331544 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9427. Min Act: -0.0000

Data Index: 374355 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8810. Min Act: -0.0000

Data Index: 464968 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1110876 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8825. Min Act: -0.0000

Data Index: 316757 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9391. Min Act: -0.0000

Data Index: 370086 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9092. Min Act: -0.0000

Data Index: 928242 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9260. Min Act: -0.0000

Data Index: 143141 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8651. Min Act: -0.0000

Data Index: 783360 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1208184 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1122066 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8721. Min Act: -0.0000

Data Index: 634910 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8602. Min Act: -0.0000

Data Index: 72008 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8586. Min Act: -0.0000

Data Index: 785706 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9281. Min Act: -0.0001

Data Index: 542187 (C4 (Web Text))

Max Activating Token Index: 879