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

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

Neuron 6115 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4595. Min Range: -1.4595

Max Act: 1.4595. Min Act: -0.0000

Data Index: 581445 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 1.4595. Min Range: -1.4595

Max Act: 1.0185. Min Act: -0.0000

Data Index: 762403 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.9820. Min Act: -0.0000

Data Index: 239346 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.9331. Min Act: -0.0000

Data Index: 809283 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8993. Min Act: -0.0000

Data Index: 787946 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8935. Min Act: -0.0000

Data Index: 290238 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8340. Min Act: -0.0000

Data Index: 231750 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1266045 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8777. Min Act: -0.0000

Data Index: 646962 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8648. Min Act: -0.0000

Data Index: 909391 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1173379 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8050. Min Act: -0.0000

Data Index: 1634 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.9534. Min Act: -0.0000

Data Index: 875351 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8133. Min Act: -0.0000

Data Index: 519782 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1343833 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8293. Min Act: -0.0000

Data Index: 615826 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.7766. Min Act: -0.0000

Data Index: 841725 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1071924 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.8195. Min Act: -0.0000

Data Index: 286284 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.4595. Min Range: -1.4595

Max Act: 0.7676. Min Act: -0.0000

Data Index: 974479 (C4 (Web Text))

Max Activating Token Index: 748