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

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

Neuron 3938 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.1592. Min Act: -0.0001

Data Index: 1106641 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.4968. Min Act: -0.0001

Data Index: 954474 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2415. Min Act: -0.0002

Data Index: 56347 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2389. Min Act: -0.0001

Data Index: 1245977 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 1.4976. Min Range: -1.4976

Max Act: 0.9784. Min Act: -0.0001

Data Index: 721915 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2318. Min Act: -0.0001

Data Index: 486689 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2496. Min Act: -0.0001

Data Index: 397591 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.0571. Min Act: -0.0002

Data Index: 795037 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2128. Min Act: -0.0001

Data Index: 758644 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.4976. Min Act: -0.0002

Data Index: 281895 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.1463. Min Act: -0.0001

Data Index: 853562 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.1790. Min Act: -0.0002

Data Index: 228849 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.0606. Min Act: -0.0002

Data Index: 4567 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.1196. Min Act: -0.0001

Data Index: 348159 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.1528. Min Act: -0.0001

Data Index: 248282 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.0570. Min Act: -0.0001

Data Index: 436200 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.1441. Min Act: -0.0001

Data Index: 1208423 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.1979. Min Act: -0.0002

Data Index: 1137683 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.1009. Min Act: -0.0002

Data Index: 182419 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.1677. Min Act: -0.0002

Data Index: 1065315 (C4 (Web Text))

Max Activating Token Index: 978