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

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

Neuron 2534 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.3569. Min Act: -0.0000

Data Index: 1292277 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.9992. Min Act: -0.0001

Data Index: 1602770 (Python Code)

Max Activating Token Index: 913

Text #2

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.8922. Min Act: -0.0000

Data Index: 960979 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.8610. Min Act: -0.0000

Data Index: 575348 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.8877. Min Act: -0.0001

Data Index: 257000 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.9124. Min Act: -0.0001

Data Index: 1556091 (Python Code)

Max Activating Token Index: 190

Text #6

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.8678. Min Act: -0.0000

Data Index: 597756 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1285824 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.7673. Min Act: -0.0001

Data Index: 1297287 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.7316. Min Act: -0.0000

Data Index: 554577 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.6509. Min Act: -0.0001

Data Index: 256446 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.7166. Min Act: -0.0001

Data Index: 128278 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.6887. Min Act: -0.0000

Data Index: 99355 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.6910. Min Act: -0.0001

Data Index: 752945 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.6881. Min Act: -0.0001

Data Index: 1210373 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1502830 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1279676 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.6809. Min Act: -0.0001

Data Index: 435639 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.6945. Min Act: -0.0001

Data Index: 509504 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.3569. Min Range: -1.3569

Max Act: 0.6568. Min Act: -0.0001

Data Index: 905414 (C4 (Web Text))

Max Activating Token Index: 703