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

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

Neuron 2529 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.6016. Min Act: -0.0001

Data Index: 1085142 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.6468. Min Act: -0.0000

Data Index: 106729 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.4786. Min Act: -0.0000

Data Index: 463767 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.3540. Min Act: -0.0000

Data Index: 1106778 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.3038. Min Act: -0.0000

Data Index: 671282 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.2675. Min Act: -0.0001

Data Index: 1340875 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.3855. Min Act: -0.0000

Data Index: 1125022 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.3387. Min Act: -0.0000

Data Index: 829088 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.3134. Min Act: -0.0000

Data Index: 1253657 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.3149. Min Act: -0.0001

Data Index: 96614 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.2508. Min Act: -0.0000

Data Index: 388467 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.2540. Min Act: -0.0001

Data Index: 1193343 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.2903. Min Act: -0.0001

Data Index: 288724 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.2748. Min Act: -0.0001

Data Index: 1185328 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.2638. Min Act: -0.0000

Data Index: 277258 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.1739. Min Act: -0.0001

Data Index: 734280 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.2376. Min Act: -0.0000

Data Index: 16927 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.2706. Min Act: -0.0001

Data Index: 481652 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.1259. Min Act: -0.0000

Data Index: 88182 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 1.6468. Min Range: -1.6468

Max Act: 1.2596. Min Act: -0.0001

Data Index: 43643 (C4 (Web Text))

Max Activating Token Index: 384