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

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

Neuron 727 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: 1.4866. Min Range: -1.4866

Max Act: 1.4866. Min Act: -0.0000

Data Index: 1307502 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1435347 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1255291 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1213534 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.7673. Min Act: -0.0000

Data Index: 715653 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1544680 (Python Code)

Max Activating Token Index: 343

Text #6

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.7089. Min Act: -0.0000

Data Index: 392273 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.6718. Min Act: -0.0000

Data Index: 43258 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1460195 (Python Code)

Max Activating Token Index: 583

Text #9

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1081393 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.6574. Min Act: -0.0000

Data Index: 36095 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.6563. Min Act: -0.0000

Data Index: 475609 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1081410 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1114166 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.7140. Min Act: -0.0000

Data Index: 520926 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.6914. Min Act: -0.0000

Data Index: 994688 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.6857. Min Act: -0.0000

Data Index: 242500 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.6641. Min Act: -0.0000

Data Index: 384963 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1488744 (Python Code)

Max Activating Token Index: 576

Text #19

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1123336 (C4 (Web Text))

Max Activating Token Index: 856