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

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

Neuron 3407 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: 0.2310. Min Range: -0.2310

Max Act: 0.2249. Min Act: -0.0001

Data Index: 1387258 (Python Code)

Max Activating Token Index: 282

Text #1

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1399811 (Python Code)

Max Activating Token Index: 552

Text #2

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1558450 (Python Code)

Max Activating Token Index: 114

Text #3

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2081. Min Act: -0.0001

Data Index: 1598230 (Python Code)

Max Activating Token Index: 462

Text #4

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1542125 (Python Code)

Max Activating Token Index: 100

Text #5

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1973. Min Act: -0.0001

Data Index: 1447974 (Python Code)

Max Activating Token Index: 487

Text #6

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1647263 (Python Code)

Max Activating Token Index: 948

Text #7

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1907. Min Act: -0.0001

Data Index: 1440164 (Python Code)

Max Activating Token Index: 558

Text #8

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1508127 (Python Code)

Max Activating Token Index: 331

Text #9

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1895. Min Act: -0.0001

Data Index: 1476185 (Python Code)

Max Activating Token Index: 805

Text #10

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1509888 (Python Code)

Max Activating Token Index: 601

Text #11

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2043. Min Act: -0.0001

Data Index: 1627531 (Python Code)

Max Activating Token Index: 629

Text #12

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1640. Min Act: -0.0001

Data Index: 1498438 (Python Code)

Max Activating Token Index: 856

Text #13

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1395193 (Python Code)

Max Activating Token Index: 815

Text #14

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1949. Min Act: -0.0001

Data Index: 1437651 (Python Code)

Max Activating Token Index: 897

Text #15

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1856. Min Act: -0.0001

Data Index: 1575432 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1945. Min Act: -0.0001

Data Index: 1416781 (Python Code)

Max Activating Token Index: 124

Text #17

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1604995 (Python Code)

Max Activating Token Index: 709

Text #18

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1656. Min Act: -0.0001

Data Index: 1554964 (Python Code)

Max Activating Token Index: 628

Text #19

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1747. Min Act: -0.0001

Data Index: 1411703 (Python Code)

Max Activating Token Index: 749