Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2963 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9804. Min Act: -0.0001

Data Index: 811947 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9172. Min Act: -0.0001

Data Index: 760877 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9281. Min Act: -0.0001

Data Index: 514334 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8904. Min Act: -0.0001

Data Index: 1310965 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9140. Min Act: -0.0001

Data Index: 902792 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9042. Min Act: -0.0001

Data Index: 592129 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7738. Min Act: -0.0001

Data Index: 911563 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8519. Min Act: -0.0001

Data Index: 482482 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9046. Min Act: -0.0001

Data Index: 98408 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7592. Min Act: -0.0001

Data Index: 1098257 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8009. Min Act: -0.0001

Data Index: 445448 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7482. Min Act: -0.0001

Data Index: 888208 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7143. Min Act: -0.0001

Data Index: 735140 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7947. Min Act: -0.0001

Data Index: 811214 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7100. Min Act: -0.0001

Data Index: 573802 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7569. Min Act: -0.0001

Data Index: 750965 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7542. Min Act: -0.0001

Data Index: 90101 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7761. Min Act: -0.0001

Data Index: 830291 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7793. Min Act: -0.0001

Data Index: 1159258 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7374. Min Act: -0.0001

Data Index: 1322156 (C4 (Web Text))

Max Activating Token Index: 8