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

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

Neuron 3605 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.4104. Min Act: 0.0002

Data Index: 317760 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.3976. Min Act: 0.0000

Data Index: 604805 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.4650. Min Act: -0.0000

Data Index: 12047 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1327889 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1859. Min Act: -0.0000

Data Index: 65652 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1854. Min Act: -0.0000

Data Index: 678268 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0932. Min Act: -0.0000

Data Index: 878747 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0651. Min Act: -0.0000

Data Index: 699016 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0815. Min Act: -0.0000

Data Index: 1330370 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0129. Min Act: 0.0000

Data Index: 236378 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0371. Min Act: -0.0000

Data Index: 30933 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0432. Min Act: -0.0000

Data Index: 354401 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 1.4650. Min Range: -1.4650

Max Act: 0.9777. Min Act: 0.0001

Data Index: 327438 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 1.4650. Min Range: -1.4650

Max Act: 0.9679. Min Act: -0.0000

Data Index: 126447 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0257. Min Act: 0.0001

Data Index: 1272353 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0735. Min Act: 0.0000

Data Index: 602117 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 1.4650. Min Range: -1.4650

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1001257 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.4650. Min Range: -1.4650

Max Act: 0.9263. Min Act: -0.0000

Data Index: 974517 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 1.4650. Min Range: -1.4650

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1091469 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 1.4650. Min Range: -1.4650

Max Act: 0.9422. Min Act: 0.0001

Data Index: 351875 (C4 (Web Text))

Max Activating Token Index: 74