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

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

Neuron 3568 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5169. Min Act: -0.0000

Data Index: 94118 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5030. Min Act: -0.0000

Data Index: 316623 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4515. Min Act: -0.0000

Data Index: 548753 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4594. Min Act: -0.0000

Data Index: 5549 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4687. Min Act: -0.0000

Data Index: 654781 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4661. Min Act: -0.0000

Data Index: 179369 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1301217 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4409. Min Act: -0.0000

Data Index: 542893 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4208. Min Act: -0.0000

Data Index: 225711 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1102897 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3980. Min Act: -0.0000

Data Index: 903073 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4144. Min Act: -0.0000

Data Index: 636201 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3907. Min Act: -0.0000

Data Index: 612142 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3902. Min Act: -0.0000

Data Index: 671695 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4152. Min Act: -0.0000

Data Index: 646872 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4139. Min Act: -0.0000

Data Index: 510576 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3977. Min Act: -0.0000

Data Index: 688741 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3884. Min Act: -0.0000

Data Index: 409181 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4053. Min Act: -0.0000

Data Index: 289249 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3927. Min Act: -0.0000

Data Index: 562206 (C4 (Web Text))

Max Activating Token Index: 536