Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1157 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3650. Min Act: -0.0001

Data Index: 1432921 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3425. Min Act: -0.0001

Data Index: 1452706 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3505. Min Act: -0.0001

Data Index: 1546894 (Python Code)

Max Activating Token Index: 104

Text #3

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3586. Min Act: -0.0001

Data Index: 1604561 (Python Code)

Max Activating Token Index: 365

Text #4

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1532965 (Python Code)

Max Activating Token Index: 526

Text #5

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3338. Min Act: -0.0001

Data Index: 1578836 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3159. Min Act: -0.0001

Data Index: 1520649 (Python Code)

Max Activating Token Index: 221

Text #7

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3343. Min Act: -0.0001

Data Index: 1433610 (Python Code)

Max Activating Token Index: 532

Text #8

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1385009 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3061. Min Act: -0.0001

Data Index: 1433363 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1371019 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3183. Min Act: -0.0001

Data Index: 1361231 (Python Code)

Max Activating Token Index: 800

Text #12

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1447351 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3172. Min Act: -0.0001

Data Index: 1613874 (Python Code)

Max Activating Token Index: 230

Text #14

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1600169 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3128. Min Act: -0.0001

Data Index: 1618614 (Python Code)

Max Activating Token Index: 389

Text #16

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2821. Min Act: -0.0001

Data Index: 1532884 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2905. Min Act: -0.0001

Data Index: 1399084 (Python Code)

Max Activating Token Index: 96

Text #18

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2674. Min Act: -0.0001

Data Index: 1458755 (Python Code)

Max Activating Token Index: 113

Text #19

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3264. Min Act: -0.0001

Data Index: 1531596 (Python Code)

Max Activating Token Index: 548