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

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

Neuron 3967 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: 0.1997. Min Range: -0.1997

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1312522 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1777. Min Act: -0.0001

Data Index: 870477 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1679. Min Act: -0.0001

Data Index: 179885 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1263675 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1246. Min Act: -0.0001

Data Index: 635337 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1172. Min Act: -0.0001

Data Index: 833195 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1230. Min Act: -0.0001

Data Index: 227394 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1163. Min Act: -0.0001

Data Index: 879029 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1164. Min Act: -0.0001

Data Index: 485229 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1111741 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1133. Min Act: -0.0001

Data Index: 822232 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1159. Min Act: -0.0001

Data Index: 631999 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1167. Min Act: -0.0001

Data Index: 49370 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1029. Min Act: -0.0001

Data Index: 629894 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1017. Min Act: -0.0001

Data Index: 277589 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1053. Min Act: -0.0001

Data Index: 323452 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1127. Min Act: -0.0001

Data Index: 696804 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1105. Min Act: -0.0001

Data Index: 597083 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.0933. Min Act: -0.0001

Data Index: 353105 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1038650 (C4 (Web Text))

Max Activating Token Index: 73