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

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

Neuron 4639 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1675. Min Act: -0.0002

Data Index: 157599 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1398. Min Act: -0.0002

Data Index: 661803 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1231. Min Act: -0.0002

Data Index: 288247 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1275. Min Act: -0.0002

Data Index: 1031064 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1358958 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1114187 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1146. Min Act: -0.0002

Data Index: 626363 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1132. Min Act: -0.0002

Data Index: 26920 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1130101 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1108. Min Act: -0.0002

Data Index: 461059 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1122. Min Act: -0.0002

Data Index: 753922 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1143. Min Act: -0.0002

Data Index: 387233 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1085. Min Act: -0.0002

Data Index: 863135 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1081. Min Act: -0.0002

Data Index: 362261 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1127. Min Act: -0.0002

Data Index: 144787 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0991. Min Act: -0.0002

Data Index: 334684 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1136. Min Act: -0.0002

Data Index: 294684 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1043. Min Act: -0.0002

Data Index: 452680 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1000. Min Act: -0.0002

Data Index: 962700 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1032. Min Act: -0.0002

Data Index: 1168682 (C4 (Web Text))

Max Activating Token Index: 448