Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 425 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2566. Min Act: 0.0000

Data Index: 237896 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2381. Min Act: -0.0000

Data Index: 49475 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2338. Min Act: -0.0000

Data Index: 477627 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2350. Min Act: -0.0000

Data Index: 27630 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1336088 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2245. Min Act: -0.0000

Data Index: 215481 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2084. Min Act: 0.0000

Data Index: 26401 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1203802 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1028060 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2155. Min Act: -0.0000

Data Index: 697093 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1029870 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2060. Min Act: -0.0000

Data Index: 772598 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2050. Min Act: -0.0000

Data Index: 221938 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2099. Min Act: -0.0000

Data Index: 399191 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1942. Min Act: -0.0000

Data Index: 428009 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1972. Min Act: -0.0001

Data Index: 271161 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2194. Min Act: -0.0000

Data Index: 886325 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.2033. Min Act: -0.0000

Data Index: 812301 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1196328 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1089736 (C4 (Web Text))

Max Activating Token Index: 597