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

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

Neuron 742 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: 0.5693. Min Range: -0.5693

Max Act: 0.5693. Min Act: -0.0000

Data Index: 287705 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5459. Min Act: -0.0000

Data Index: 295646 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5393. Min Act: -0.0000

Data Index: 453992 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4972. Min Act: -0.0000

Data Index: 204727 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1036810 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5122. Min Act: -0.0000

Data Index: 955580 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1215219 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1235433 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5020. Min Act: -0.0000

Data Index: 537347 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4857. Min Act: -0.0000

Data Index: 33836 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5058. Min Act: -0.0000

Data Index: 921680 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5004. Min Act: -0.0000

Data Index: 200431 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4857. Min Act: -0.0000

Data Index: 138934 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1169689 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4681. Min Act: -0.0000

Data Index: 576609 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4818. Min Act: -0.0000

Data Index: 74804 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4379. Min Act: -0.0000

Data Index: 26339 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4328. Min Act: 0.0000

Data Index: 1114466 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1429437 (Python Code)

Max Activating Token Index: 991

Text #19

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4409. Min Act: -0.0000

Data Index: 422750 (C4 (Web Text))

Max Activating Token Index: 950