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

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

Neuron 5807 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.3080. Min Act: -0.0000

Data Index: 1626166 (Python Code)

Max Activating Token Index: 114

Text #1

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.2442. Min Act: -0.0000

Data Index: 1413761 (Python Code)

Max Activating Token Index: 867

Text #2

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.2973. Min Act: -0.0000

Data Index: 1389405 (Python Code)

Max Activating Token Index: 409

Text #3

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1564529 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1576221 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.2167. Min Act: -0.0000

Data Index: 1645914 (Python Code)

Max Activating Token Index: 595

Text #6

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1591163 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1427. Min Act: -0.0000

Data Index: 1425212 (Python Code)

Max Activating Token Index: 481

Text #8

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1410872 (Python Code)

Max Activating Token Index: 143

Text #9

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1583244 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1455194 (Python Code)

Max Activating Token Index: 481

Text #11

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1476818 (Python Code)

Max Activating Token Index: 538

Text #12

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0885. Min Act: -0.0000

Data Index: 1394394 (Python Code)

Max Activating Token Index: 507

Text #13

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0511. Min Act: -0.0000

Data Index: 1466222 (Python Code)

Max Activating Token Index: 902

Text #14

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1443306 (Python Code)

Max Activating Token Index: 231

Text #15

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0486. Min Act: -0.0000

Data Index: 1444765 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0235. Min Act: -0.0000

Data Index: 1470668 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1510550 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1483691 (Python Code)

Max Activating Token Index: 878

Text #19

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0394. Min Act: -0.0000

Data Index: 1424563 (Python Code)

Max Activating Token Index: 243