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

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

Neuron 4041 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2387. Min Act: -0.0000

Data Index: 50276 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2106. Min Act: -0.0000

Data Index: 630561 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2186. Min Act: -0.0000

Data Index: 950968 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2161. Min Act: -0.0000

Data Index: 837127 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1159550 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2257. Min Act: -0.0000

Data Index: 256643 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2120. Min Act: -0.0001

Data Index: 647058 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2218. Min Act: -0.0000

Data Index: 908207 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2038. Min Act: -0.0000

Data Index: 643845 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1250426 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1289947 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2131. Min Act: -0.0000

Data Index: 683254 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1209850 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1969. Min Act: -0.0000

Data Index: 477418 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1154391 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1196363 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1947. Min Act: -0.0000

Data Index: 12341 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2090. Min Act: -0.0000

Data Index: 521236 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1026721 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1991. Min Act: -0.0000

Data Index: 145460 (C4 (Web Text))

Max Activating Token Index: 995