Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3604 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.4659. Min Act: -0.0000

Data Index: 271414 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0380. Min Act: -0.0001

Data Index: 947158 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9850. Min Act: -0.0000

Data Index: 223234 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9357. Min Act: -0.0000

Data Index: 1239823 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1345. Min Act: -0.0001

Data Index: 246196 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0001. Min Act: -0.0000

Data Index: 858141 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9773. Min Act: -0.0001

Data Index: 519141 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.8821. Min Act: -0.0001

Data Index: 870421 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9387. Min Act: -0.0001

Data Index: 986476 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9014. Min Act: -0.0000

Data Index: 709498 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.8857. Min Act: -0.0000

Data Index: 272559 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9687. Min Act: -0.0000

Data Index: 719757 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.8530. Min Act: -0.0001

Data Index: 618042 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9019. Min Act: -0.0000

Data Index: 198243 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9196. Min Act: -0.0000

Data Index: 1125579 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1101238 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.8757. Min Act: -0.0000

Data Index: 568860 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1055824 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.8571. Min Act: -0.0001

Data Index: 352130 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.8485. Min Act: -0.0000

Data Index: 58302 (C4 (Web Text))

Max Activating Token Index: 387