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

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

Neuron 2121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.6667. Min Act: -0.0000

Data Index: 899072 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.5906. Min Act: -0.0000

Data Index: 501782 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.4691. Min Act: -0.0000

Data Index: 757103 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.3624. Min Act: -0.0000

Data Index: 1143071 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.4082. Min Act: -0.0000

Data Index: 607532 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.3837. Min Act: -0.0000

Data Index: 1045113 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.2265. Min Act: -0.0000

Data Index: 149848 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.3516. Min Act: -0.0000

Data Index: 82553 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.3336. Min Act: -0.0000

Data Index: 345984 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.3317. Min Act: -0.0000

Data Index: 1184627 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.0982. Min Act: -0.0000

Data Index: 375311 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.2301. Min Act: -0.0000

Data Index: 261434 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.0887. Min Act: -0.0000

Data Index: 566019 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 2.6667. Min Range: -2.6667

Max Act: 2.0175. Min Act: -0.0000

Data Index: 690622 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 2.6667. Min Range: -2.6667

Max Act: 1.8659. Min Act: -0.0000

Data Index: 108742 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 2.6667. Min Range: -2.6667

Max Act: 1.8713. Min Act: -0.0000

Data Index: 296355 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 2.6667. Min Range: -2.6667

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1239047 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 2.6667. Min Range: -2.6667

Max Act: 1.9048. Min Act: -0.0000

Data Index: 978996 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 2.6667. Min Range: -2.6667

Max Act: 1.7909. Min Act: -0.0000

Data Index: 547807 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 2.6667. Min Range: -2.6667

Max Act: 1.7780. Min Act: -0.0000

Data Index: 581384 (C4 (Web Text))

Max Activating Token Index: 779