Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1503 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3341. Min Range: -2.3341

Max Act: 2.3341. Min Act: -0.0000

Data Index: 66352 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 2.3341. Min Range: -2.3341

Max Act: 2.1889. Min Act: -0.0000

Data Index: 778424 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.9874. Min Act: -0.0000

Data Index: 395478 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.8073. Min Act: -0.0000

Data Index: 115762 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.6498. Min Act: -0.0000

Data Index: 1038568 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.9754. Min Act: -0.0000

Data Index: 143628 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.7338. Min Act: -0.0000

Data Index: 682727 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.5363. Min Act: -0.0000

Data Index: 262700 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.7338. Min Act: -0.0000

Data Index: 44875 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.6228. Min Act: -0.0000

Data Index: 1253239 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.6188. Min Act: -0.0000

Data Index: 459224 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.8157. Min Act: -0.0000

Data Index: 557213 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.6865. Min Act: -0.0000

Data Index: 616306 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.5950. Min Act: -0.0000

Data Index: 990264 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.6836. Min Act: -0.0000

Data Index: 837393 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.5869. Min Act: -0.0000

Data Index: 491193 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.5357. Min Act: -0.0000

Data Index: 65290 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.6305. Min Act: -0.0000

Data Index: 1194761 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.6324. Min Act: -0.0000

Data Index: 405017 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 2.3341. Min Range: -2.3341

Max Act: 1.5298. Min Act: -0.0000

Data Index: 1039813 (C4 (Web Text))

Max Activating Token Index: 405