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

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

Neuron 3890 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: 0.7918. Min Range: -0.7918

Max Act: 0.7918. Min Act: -0.0001

Data Index: 709558 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.7573. Min Act: -0.0001

Data Index: 1022995 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6631. Min Act: -0.0001

Data Index: 804782 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.7110. Min Act: -0.0001

Data Index: 1330859 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6231. Min Act: -0.0001

Data Index: 494358 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6180. Min Act: -0.0001

Data Index: 101680 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1116350 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6031. Min Act: -0.0001

Data Index: 428345 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5986. Min Act: -0.0001

Data Index: 363181 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5841. Min Act: -0.0001

Data Index: 1044216 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5562. Min Act: -0.0000

Data Index: 454591 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5738. Min Act: -0.0001

Data Index: 937922 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5659. Min Act: -0.0001

Data Index: 116116 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5614. Min Act: -0.0001

Data Index: 1054660 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5754. Min Act: -0.0001

Data Index: 1098407 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5845. Min Act: -0.0001

Data Index: 416839 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5266. Min Act: -0.0001

Data Index: 945400 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5467. Min Act: -0.0001

Data Index: 556491 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5568. Min Act: -0.0001

Data Index: 148737 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5382. Min Act: -0.0000

Data Index: 576133 (C4 (Web Text))

Max Activating Token Index: 362