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

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

Neuron 411 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1468084 (Python Code)

Max Activating Token Index: 838

Text #1

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0986. Min Act: -0.0001

Data Index: 739105 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1423368 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1402656 (Python Code)

Max Activating Token Index: 681

Text #4

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0957. Min Act: -0.0001

Data Index: 961302 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0955. Min Act: -0.0001

Data Index: 296036 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1462752 (Python Code)

Max Activating Token Index: 271

Text #7

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0921. Min Act: -0.0001

Data Index: 438413 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0948. Min Act: -0.0001

Data Index: 221248 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0826. Min Act: -0.0001

Data Index: 305072 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0931. Min Act: -0.0001

Data Index: 580821 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0968. Min Act: -0.0001

Data Index: 427003 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0865. Min Act: -0.0001

Data Index: 95331 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1583534 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0921. Min Act: -0.0001

Data Index: 815911 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1555067 (Python Code)

Max Activating Token Index: 938

Text #16

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0883. Min Act: -0.0001

Data Index: 592138 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0894. Min Act: -0.0001

Data Index: 345863 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1523372 (Python Code)

Max Activating Token Index: 955

Text #19

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0843. Min Act: -0.0001

Data Index: 422415 (C4 (Web Text))

Max Activating Token Index: 268