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

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

Neuron 4092 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0189. Min Range: -1.0189

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1531137 (Python Code)

Max Activating Token Index: 474

Text #1

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1320171 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8776. Min Act: -0.0000

Data Index: 923546 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8926. Min Act: -0.0000

Data Index: 404491 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1607664 (Python Code)

Max Activating Token Index: 139

Text #5

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.9551. Min Act: -0.0000

Data Index: 365349 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.9127. Min Act: -0.0000

Data Index: 46070 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.9339. Min Act: -0.0000

Data Index: 821612 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.6963. Min Act: -0.0000

Data Index: 492936 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8410. Min Act: -0.0000

Data Index: 763488 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8937. Min Act: -0.0000

Data Index: 935509 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.7857. Min Act: -0.0000

Data Index: 583232 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8600. Min Act: -0.0000

Data Index: 133215 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8851. Min Act: -0.0000

Data Index: 719299 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8351. Min Act: -0.0000

Data Index: 458335 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.7761. Min Act: -0.0000

Data Index: 292242 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.7714. Min Act: -0.0000

Data Index: 857527 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1212696 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1292871 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8203. Min Act: -0.0000

Data Index: 76487 (C4 (Web Text))

Max Activating Token Index: 802