Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2323 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.1428. Min Act: -0.0001

Data Index: 76733 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.2423. Min Act: -0.0001

Data Index: 269194 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.1366. Min Act: -0.0001

Data Index: 520171 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.1026. Min Act: -0.0001

Data Index: 570728 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9867. Min Act: -0.0001

Data Index: 660169 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0587. Min Act: -0.0001

Data Index: 955981 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9982. Min Act: -0.0001

Data Index: 621766 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9557. Min Act: -0.0001

Data Index: 129994 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0037. Min Act: -0.0001

Data Index: 743832 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0556. Min Act: -0.0001

Data Index: 1279898 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9335. Min Act: -0.0001

Data Index: 310831 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9641. Min Act: -0.0001

Data Index: 827116 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9572. Min Act: -0.0001

Data Index: 16512 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0482. Min Act: -0.0001

Data Index: 855843 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.8886. Min Act: -0.0001

Data Index: 937555 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9355. Min Act: -0.0001

Data Index: 640170 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9477. Min Act: -0.0001

Data Index: 840933 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9478. Min Act: -0.0001

Data Index: 912164 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9649. Min Act: -0.0001

Data Index: 656767 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.7954. Min Act: -0.0001

Data Index: 990360 (C4 (Web Text))

Max Activating Token Index: 536