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

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

Neuron 1712 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.9148. Min Act: -0.0001

Data Index: 160897 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7964. Min Act: -0.0001

Data Index: 589438 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7840. Min Act: -0.0001

Data Index: 268121 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7415. Min Act: -0.0000

Data Index: 114655 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.8116. Min Act: -0.0001

Data Index: 143546 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6713. Min Act: -0.0001

Data Index: 315194 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7585. Min Act: -0.0000

Data Index: 330615 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7074. Min Act: -0.0001

Data Index: 579052 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7142. Min Act: -0.0001

Data Index: 1347051 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7225. Min Act: -0.0001

Data Index: 988208 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1197755 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1157264 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6854. Min Act: -0.0000

Data Index: 435701 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7249. Min Act: -0.0001

Data Index: 392286 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7991. Min Act: -0.0001

Data Index: 127199 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6246. Min Act: -0.0001

Data Index: 563810 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1194284 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1195754 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6238. Min Act: -0.0001

Data Index: 479556 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6092. Min Act: -0.0001

Data Index: 710199 (C4 (Web Text))

Max Activating Token Index: 145