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

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

Neuron 1080 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1495. Min Act: -0.0001

Data Index: 1495358 (Python Code)

Max Activating Token Index: 759

Text #1

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.9903. Min Act: -0.0001

Data Index: 1447854 (Python Code)

Max Activating Token Index: 468

Text #2

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.9270. Min Act: -0.0001

Data Index: 1592579 (Python Code)

Max Activating Token Index: 146

Text #3

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.2167. Min Act: -0.0002

Data Index: 1591246 (Python Code)

Max Activating Token Index: 461

Text #4

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.0547. Min Act: -0.0001

Data Index: 1481028 (Python Code)

Max Activating Token Index: 73

Text #5

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.9056. Min Act: -0.0001

Data Index: 1408461 (Python Code)

Max Activating Token Index: 889

Text #6

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.8898. Min Act: -0.0001

Data Index: 1563785 (Python Code)

Max Activating Token Index: 634

Text #7

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.9958. Min Act: -0.0001

Data Index: 1446361 (Python Code)

Max Activating Token Index: 1007

Text #8

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1077. Min Act: -0.0001

Data Index: 1517496 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.9198. Min Act: -0.0001

Data Index: 1412134 (Python Code)

Max Activating Token Index: 285

Text #10

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.8980. Min Act: -0.0001

Data Index: 1642687 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.7424. Min Act: -0.0001

Data Index: 1383118 (Python Code)

Max Activating Token Index: 514

Text #12

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.8311. Min Act: -0.0001

Data Index: 1441411 (Python Code)

Max Activating Token Index: 1002

Text #13

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.8427. Min Act: -0.0001

Data Index: 1652979 (Python Code)

Max Activating Token Index: 257

Text #14

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.7958. Min Act: -0.0001

Data Index: 1497969 (Python Code)

Max Activating Token Index: 603

Text #15

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.9352. Min Act: -0.0001

Data Index: 1573470 (Python Code)

Max Activating Token Index: 653

Text #16

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.7814. Min Act: -0.0001

Data Index: 1432625 (Python Code)

Max Activating Token Index: 618

Text #17

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.7695. Min Act: -0.0001

Data Index: 1522903 (Python Code)

Max Activating Token Index: 58

Text #18

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.7763. Min Act: -0.0001

Data Index: 1594434 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 3.2167. Min Range: -3.2167

Max Act: 2.7530. Min Act: -0.0001

Data Index: 1557237 (Python Code)

Max Activating Token Index: 105