Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2021 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1236. Min Act: -0.0004

Data Index: 1099543 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1201. Min Act: -0.0004

Data Index: 834803 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1174. Min Act: -0.0004

Data Index: 1051746 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1133. Min Act: -0.0004

Data Index: 705781 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1175. Min Act: -0.0004

Data Index: 1279521 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1174. Min Act: -0.0004

Data Index: 880654 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1023. Min Act: -0.0004

Data Index: 1184720 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1150. Min Act: -0.0004

Data Index: 1109217 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1064. Min Act: -0.0004

Data Index: 806488 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1142. Min Act: -0.0004

Data Index: 656980 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1184. Min Act: -0.0004

Data Index: 311949 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1277. Min Act: -0.0004

Data Index: 900383 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1229. Min Act: -0.0004

Data Index: 1187515 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1085. Min Act: -0.0004

Data Index: 29802 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1212. Min Act: -0.0004

Data Index: 752512 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1084. Min Act: -0.0004

Data Index: 703428 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1115. Min Act: -0.0004

Data Index: 393782 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1158. Min Act: -0.0004

Data Index: 509274 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1104. Min Act: -0.0004

Data Index: 117947 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1146. Min Act: -0.0004

Data Index: 1119892 (C4 (Web Text))

Max Activating Token Index: 679