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

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

Neuron 5928 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2547. Min Act: -0.0000

Data Index: 1326795 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2683. Min Act: -0.0000

Data Index: 439676 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2382. Min Act: -0.0000

Data Index: 17426 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2489. Min Act: -0.0001

Data Index: 1107091 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2423. Min Act: -0.0000

Data Index: 173427 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2270. Min Act: -0.0000

Data Index: 967212 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2434. Min Act: -0.0000

Data Index: 574792 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2329. Min Act: -0.0000

Data Index: 376220 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2215. Min Act: -0.0001

Data Index: 1153847 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2280. Min Act: -0.0001

Data Index: 552291 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1988. Min Act: -0.0000

Data Index: 297966 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2017. Min Act: -0.0001

Data Index: 153767 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2089. Min Act: -0.0001

Data Index: 994927 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1990. Min Act: -0.0001

Data Index: 964727 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1956. Min Act: -0.0000

Data Index: 1221225 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1833. Min Act: -0.0001

Data Index: 345449 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1999. Min Act: -0.0000

Data Index: 66004 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1977. Min Act: -0.0001

Data Index: 496212 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1977. Min Act: -0.0001

Data Index: 861307 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1033325 (C4 (Web Text))

Max Activating Token Index: 425