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

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

Neuron 2313 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1070346 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1028301 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.4107. Min Act: -0.0000

Data Index: 65000 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3876. Min Act: -0.0000

Data Index: 477655 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3560. Min Act: -0.0000

Data Index: 309619 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3954. Min Act: -0.0000

Data Index: 101042 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3686. Min Act: -0.0000

Data Index: 14291 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3991. Min Act: -0.0000

Data Index: 386856 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3545. Min Act: -0.0000

Data Index: 46233 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1294129 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3465. Min Act: -0.0000

Data Index: 151988 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1320431 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3457. Min Act: -0.0000

Data Index: 91641 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3693. Min Act: -0.0000

Data Index: 786388 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3263. Min Act: -0.0000

Data Index: 733957 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1275697 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3193. Min Act: -0.0000

Data Index: 560087 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1183926 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3204. Min Act: -0.0000

Data Index: 713834 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1315329 (C4 (Web Text))

Max Activating Token Index: 154