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

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

Neuron 648 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.9304. Min Act: -0.0000

Data Index: 142695 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.9514. Min Act: -0.0000

Data Index: 665837 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.9181. Min Act: -0.0000

Data Index: 215546 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.7051. Min Act: -0.0000

Data Index: 483333 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.7294. Min Act: -0.0000

Data Index: 319619 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.7488. Min Act: -0.0000

Data Index: 288093 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.7644. Min Act: -0.0000

Data Index: 66420 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.5232. Min Act: -0.0000

Data Index: 1088489 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.4331. Min Act: -0.0000

Data Index: 170087 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.5408. Min Act: -0.0000

Data Index: 1298671 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.2051. Min Act: -0.0000

Data Index: 1261190 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.5259. Min Act: -0.0000

Data Index: 185733 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.3001. Min Act: -0.0000

Data Index: 463156 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.0996. Min Act: -0.0000

Data Index: 971611 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.4747. Min Act: -0.0000

Data Index: 1353818 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.2983. Min Act: -0.0000

Data Index: 1306953 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.2450. Min Act: -0.0000

Data Index: 454750 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.0621. Min Act: -0.0000

Data Index: 1208368 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.2141. Min Act: -0.0000

Data Index: 711724 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 7.9514. Min Range: -7.9514

Max Act: 7.5765. Min Act: -0.0000

Data Index: 744320 (C4 (Web Text))

Max Activating Token Index: 723