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

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

Neuron 4882 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1516. Min Act: -0.0001

Data Index: 280806 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1174617 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1211. Min Act: -0.0001

Data Index: 563638 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1296. Min Act: -0.0001

Data Index: 516407 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1243. Min Act: -0.0001

Data Index: 708351 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0970. Min Act: -0.0001

Data Index: 325894 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1213544 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1133. Min Act: -0.0001

Data Index: 721426 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1350023 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1509473 (Python Code)

Max Activating Token Index: 852

Text #12

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1028. Min Act: -0.0001

Data Index: 259899 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0981. Min Act: -0.0001

Data Index: 369152 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1397200 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0986. Min Act: -0.0001

Data Index: 91328 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0973. Min Act: -0.0001

Data Index: 589323 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1214479 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1532586 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0976. Min Act: -0.0001

Data Index: 928548 (C4 (Web Text))

Max Activating Token Index: 177