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

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

Neuron 2587 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: 1.3180. Min Range: -1.3180

Max Act: 1.3180. Min Act: -0.0001

Data Index: 326835 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 1.3180. Min Range: -1.3180

Max Act: 1.2451. Min Act: 0.0000

Data Index: 919177 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 1.3180. Min Range: -1.3180

Max Act: 1.0940. Min Act: -0.0001

Data Index: 634649 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 1.3180. Min Range: -1.3180

Max Act: 1.1576. Min Act: -0.0001

Data Index: 177189 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 1.3180. Min Range: -1.3180

Max Act: 0.9950. Min Act: -0.0001

Data Index: 508786 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 1.3180. Min Range: -1.3180

Max Act: 1.0095. Min Act: -0.0001

Data Index: 277743 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 1.3180. Min Range: -1.3180

Max Act: 1.0345. Min Act: -0.0001

Data Index: 1028343 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 1.3180. Min Range: -1.3180

Max Act: 1.0133. Min Act: -0.0001

Data Index: 873951 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.3180. Min Range: -1.3180

Max Act: 1.0484. Min Act: -0.0001

Data Index: 1236010 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 1.3180. Min Range: -1.3180

Max Act: 0.9595. Min Act: -0.0001

Data Index: 1109723 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.3180. Min Range: -1.3180

Max Act: 0.8553. Min Act: 0.0001

Data Index: 16037 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.3180. Min Range: -1.3180

Max Act: 0.9391. Min Act: -0.0001

Data Index: 480547 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.3180. Min Range: -1.3180

Max Act: 0.8764. Min Act: -0.0000

Data Index: 1319274 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 1.3180. Min Range: -1.3180

Max Act: 0.8915. Min Act: -0.0001

Data Index: 1083975 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 1.3180. Min Range: -1.3180

Max Act: 1.0099. Min Act: 0.0000

Data Index: 613890 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 1.3180. Min Range: -1.3180

Max Act: 0.9294. Min Act: -0.0000

Data Index: 988912 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.3180. Min Range: -1.3180

Max Act: 0.9286. Min Act: -0.0001

Data Index: 249334 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 1.3180. Min Range: -1.3180

Max Act: 0.8854. Min Act: -0.0001

Data Index: 1229117 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 1.3180. Min Range: -1.3180

Max Act: 0.9204. Min Act: -0.0001

Data Index: 1128324 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 1.3180. Min Range: -1.3180

Max Act: 0.8844. Min Act: 0.0000

Data Index: 191890 (C4 (Web Text))

Max Activating Token Index: 364