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

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

Neuron 5714 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2409. Min Act: -0.0000

Data Index: 931476 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2453. Min Act: -0.0000

Data Index: 557794 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2419. Min Act: -0.0000

Data Index: 718657 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2322. Min Act: -0.0000

Data Index: 11494 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1286095 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2293. Min Act: -0.0000

Data Index: 79737 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2182. Min Act: -0.0000

Data Index: 733364 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1012986 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1308602 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2104. Min Act: -0.0000

Data Index: 29829 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1024474 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.1989. Min Act: -0.0000

Data Index: 831558 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2197. Min Act: -0.0000

Data Index: 373178 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2058. Min Act: -0.0000

Data Index: 318527 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2050. Min Act: -0.0000

Data Index: 12808 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2020. Min Act: -0.0000

Data Index: 143233 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.1867. Min Act: -0.0000

Data Index: 818206 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.1964. Min Act: -0.0000

Data Index: 314067 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1327410 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1079148 (C4 (Web Text))

Max Activating Token Index: 272