Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 32 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2773. Min Act: -0.0002

Data Index: 1579767 (Python Code)

Max Activating Token Index: 815

Text #1

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2240. Min Act: -0.0002

Data Index: 1613959 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2296. Min Act: -0.0002

Data Index: 1637721 (Python Code)

Max Activating Token Index: 966

Text #3

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2486. Min Act: -0.0002

Data Index: 1542492 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2126. Min Act: -0.0002

Data Index: 1404986 (Python Code)

Max Activating Token Index: 644

Text #5

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2020. Min Act: -0.0002

Data Index: 1478520 (Python Code)

Max Activating Token Index: 210

Text #6

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1990. Min Act: -0.0002

Data Index: 1423172 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2002. Min Act: -0.0002

Data Index: 1560151 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2056. Min Act: -0.0002

Data Index: 1497230 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2046. Min Act: -0.0002

Data Index: 1431153 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1906. Min Act: -0.0002

Data Index: 1395138 (Python Code)

Max Activating Token Index: 894

Text #11

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2022. Min Act: -0.0002

Data Index: 1417451 (Python Code)

Max Activating Token Index: 490

Text #12

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2088. Min Act: -0.0002

Data Index: 1620135 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1945. Min Act: -0.0002

Data Index: 1469069 (Python Code)

Max Activating Token Index: 769

Text #14

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1973. Min Act: -0.0002

Data Index: 1647785 (Python Code)

Max Activating Token Index: 212

Text #15

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1974. Min Act: -0.0002

Data Index: 1567020 (Python Code)

Max Activating Token Index: 155

Text #16

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1978. Min Act: -0.0002

Data Index: 1652499 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2032. Min Act: -0.0002

Data Index: 1579751 (Python Code)

Max Activating Token Index: 675

Text #18

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1948. Min Act: -0.0002

Data Index: 1502101 (Python Code)

Max Activating Token Index: 470

Text #19

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1952. Min Act: -0.0002

Data Index: 1442683 (Python Code)

Max Activating Token Index: 816