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

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

Neuron 3551 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8705. Min Range: -5.8705

Max Act: 5.8705. Min Act: -0.0000

Data Index: 677297 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 5.8705. Min Range: -5.8705

Max Act: 5.5910. Min Act: -0.0000

Data Index: 644140 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 5.8705. Min Range: -5.8705

Max Act: 5.5686. Min Act: -0.0000

Data Index: 988655 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 5.8705. Min Range: -5.8705

Max Act: 5.3629. Min Act: -0.0000

Data Index: 257367 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 5.8705. Min Range: -5.8705

Max Act: 5.4936. Min Act: -0.0000

Data Index: 43817 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 5.8705. Min Range: -5.8705

Max Act: 5.1304. Min Act: -0.0000

Data Index: 1002010 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 5.8705. Min Range: -5.8705

Max Act: 5.0940. Min Act: -0.0000

Data Index: 29965 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 5.8705. Min Range: -5.8705

Max Act: 5.3712. Min Act: -0.0000

Data Index: 986023 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 5.8705. Min Range: -5.8705

Max Act: 5.1027. Min Act: -0.0000

Data Index: 1045089 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 5.8705. Min Range: -5.8705

Max Act: 5.1784. Min Act: -0.0000

Data Index: 1238934 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 5.8705. Min Range: -5.8705

Max Act: 5.0387. Min Act: -0.0000

Data Index: 1327246 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 5.8705. Min Range: -5.8705

Max Act: 4.8663. Min Act: -0.0000

Data Index: 529597 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 5.8705. Min Range: -5.8705

Max Act: 4.8111. Min Act: -0.0000

Data Index: 180563 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 5.8705. Min Range: -5.8705

Max Act: 4.6252. Min Act: -0.0001

Data Index: 553613 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 5.8705. Min Range: -5.8705

Max Act: 4.8228. Min Act: -0.0000

Data Index: 1277332 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 5.8705. Min Range: -5.8705

Max Act: 4.5421. Min Act: -0.0000

Data Index: 614249 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 5.8705. Min Range: -5.8705

Max Act: 4.3392. Min Act: -0.0000

Data Index: 1283382 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 5.8705. Min Range: -5.8705

Max Act: 4.2670. Min Act: -0.0000

Data Index: 193534 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 5.8705. Min Range: -5.8705

Max Act: 4.2106. Min Act: -0.0000

Data Index: 1026444 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 5.8705. Min Range: -5.8705

Max Act: 4.4822. Min Act: -0.0000

Data Index: 512050 (C4 (Web Text))

Max Activating Token Index: 811