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

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

Neuron 749 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: 0.5827. Min Range: -0.5827

Max Act: 0.5503. Min Act: -0.0001

Data Index: 886348 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5493. Min Act: -0.0001

Data Index: 1190900 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5827. Min Act: -0.0001

Data Index: 373818 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5252. Min Act: -0.0001

Data Index: 482895 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5756. Min Act: -0.0001

Data Index: 211251 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5584. Min Act: -0.0001

Data Index: 507987 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5361. Min Act: -0.0001

Data Index: 264774 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5369. Min Act: -0.0001

Data Index: 135637 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5602. Min Act: -0.0001

Data Index: 421035 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5314. Min Act: -0.0001

Data Index: 662137 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5111. Min Act: -0.0001

Data Index: 1327105 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4965. Min Act: -0.0001

Data Index: 917080 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5284. Min Act: -0.0001

Data Index: 352146 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5121. Min Act: -0.0001

Data Index: 393923 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4773. Min Act: -0.0001

Data Index: 956479 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5228. Min Act: -0.0001

Data Index: 512702 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5047. Min Act: -0.0001

Data Index: 1205898 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5129. Min Act: -0.0001

Data Index: 1202748 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5050. Min Act: -0.0001

Data Index: 483883 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4963. Min Act: -0.0001

Data Index: 864215 (C4 (Web Text))

Max Activating Token Index: 993