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

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

Neuron 486 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.7023. Min Act: -0.0000

Data Index: 246736 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.9073. Min Act: -0.0000

Data Index: 398101 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.6659. Min Act: -0.0000

Data Index: 123529 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.5859. Min Act: -0.0000

Data Index: 1103358 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.5705. Min Act: -0.0000

Data Index: 432304 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.4874. Min Act: -0.0000

Data Index: 297329 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.3914. Min Act: -0.0000

Data Index: 1536982 (Python Code)

Max Activating Token Index: 334

Text #7

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.4588. Min Act: -0.0000

Data Index: 913500 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.4640. Min Act: -0.0000

Data Index: 1128673 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.4668. Min Act: -0.0000

Data Index: 888996 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.4489. Min Act: -0.0000

Data Index: 1236284 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.3506. Min Act: -0.0000

Data Index: 527005 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.3138. Min Act: -0.0000

Data Index: 697541 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1072947 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.2944. Min Act: -0.0000

Data Index: 1381405 (Python Code)

Max Activating Token Index: 424

Text #15

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.2512. Min Act: -0.0000

Data Index: 108659 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.2782. Min Act: -0.0000

Data Index: 1406908 (Python Code)

Max Activating Token Index: 401

Text #17

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.2380. Min Act: -0.0000

Data Index: 731957 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.2637. Min Act: -0.0000

Data Index: 208420 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 1.9073. Min Range: -1.9073

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1414340 (Python Code)

Max Activating Token Index: 199