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

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

Neuron 4935 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.8094. Min Act: -0.0001

Data Index: 371925 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7795. Min Act: -0.0001

Data Index: 1314139 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7902. Min Act: -0.0001

Data Index: 817945 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7910. Min Act: -0.0001

Data Index: 236911 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7646. Min Act: -0.0001

Data Index: 759977 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7952. Min Act: -0.0001

Data Index: 1268850 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7791. Min Act: -0.0001

Data Index: 364341 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7382. Min Act: -0.0001

Data Index: 891396 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7396. Min Act: -0.0001

Data Index: 784819 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7194. Min Act: -0.0001

Data Index: 249304 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7669. Min Act: -0.0001

Data Index: 460135 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7062. Min Act: -0.0001

Data Index: 1102686 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7709. Min Act: -0.0001

Data Index: 806997 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7354. Min Act: -0.0001

Data Index: 251479 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7266. Min Act: -0.0001

Data Index: 476880 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7568. Min Act: -0.0001

Data Index: 977525 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7571. Min Act: -0.0001

Data Index: 276529 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6976. Min Act: -0.0001

Data Index: 1192766 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6672. Min Act: -0.0001

Data Index: 524918 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7493. Min Act: -0.0001

Data Index: 962382 (C4 (Web Text))

Max Activating Token Index: 999