Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3270 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8963. Min Act: -0.0000

Data Index: 178431 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1257527 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.9755. Min Act: -0.0000

Data Index: 302860 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1254092 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8973. Min Act: -0.0000

Data Index: 234219 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1301310 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8125. Min Act: -0.0000

Data Index: 100554 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8586. Min Act: -0.0000

Data Index: 359789 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7648. Min Act: -0.0000

Data Index: 123023 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1251951 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7817. Min Act: -0.0000

Data Index: 223310 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7657. Min Act: -0.0000

Data Index: 670624 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1063950 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1214812 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7405. Min Act: -0.0000

Data Index: 1186582 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1026261 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7037. Min Act: -0.0000

Data Index: 603486 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6305. Min Act: -0.0000

Data Index: 82756 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6708. Min Act: -0.0000

Data Index: 368824 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1332755 (C4 (Web Text))

Max Activating Token Index: 833