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

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

Neuron 526 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2103. Min Range: -2.2103

Max Act: 2.2103. Min Act: -0.0000

Data Index: 532592 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 2.2103. Min Range: -2.2103

Max Act: 2.0256. Min Act: -0.0000

Data Index: 868996 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.8779. Min Act: -0.0000

Data Index: 153519 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1133224 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.7227. Min Act: -0.0000

Data Index: 405463 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.2962. Min Act: -0.0000

Data Index: 562215 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.6089. Min Act: -0.0000

Data Index: 398711 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.3978. Min Act: -0.0000

Data Index: 462879 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.3737. Min Act: -0.0000

Data Index: 375478 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.4515. Min Act: -0.0000

Data Index: 581769 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.5212. Min Act: -0.0000

Data Index: 1189927 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.4454. Min Act: -0.0000

Data Index: 850697 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.4431. Min Act: -0.0000

Data Index: 555969 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1104706 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.1791. Min Act: -0.0000

Data Index: 472099 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.2520. Min Act: -0.0000

Data Index: 767152 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.2421. Min Act: -0.0000

Data Index: 726546 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.3613. Min Act: -0.0000

Data Index: 685599 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.2930. Min Act: -0.0000

Data Index: 887776 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.2108. Min Act: -0.0000

Data Index: 980590 (C4 (Web Text))

Max Activating Token Index: 659