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

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

Neuron 1380 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.3638. Min Act: 0.0000

Data Index: 37014 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.3174. Min Act: -0.0000

Data Index: 217813 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.3042. Min Act: 0.0000

Data Index: 511945 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.3915. Min Act: 0.0000

Data Index: 198561 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.2677. Min Act: -0.0000

Data Index: 581205 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.2832. Min Act: -0.0000

Data Index: 699468 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.2509. Min Act: 0.0000

Data Index: 597103 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.2445. Min Act: -0.0000

Data Index: 1015026 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1729. Min Act: -0.0000

Data Index: 1057642 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.2019. Min Act: -0.0000

Data Index: 19351 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1921. Min Act: -0.0000

Data Index: 414314 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1144694 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.2066. Min Act: -0.0000

Data Index: 368711 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1603. Min Act: 0.0001

Data Index: 162051 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1067841 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1108. Min Act: 0.0000

Data Index: 572505 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1081395 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1337. Min Act: -0.0000

Data Index: 496871 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1330. Min Act: -0.0000

Data Index: 1143762 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1168894 (C4 (Web Text))

Max Activating Token Index: 29