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

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

Neuron 748 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: 2.8146. Min Range: -2.8146

Max Act: 2.8146. Min Act: -0.0000

Data Index: 659519 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.5420. Min Act: -0.0000

Data Index: 235584 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.4487. Min Act: -0.0000

Data Index: 971039 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.3033. Min Act: -0.0000

Data Index: 933149 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.3568. Min Act: -0.0000

Data Index: 167225 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.2579. Min Act: -0.0000

Data Index: 592440 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.2544. Min Act: -0.0000

Data Index: 4977 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.2264. Min Act: -0.0000

Data Index: 1287552 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.2231. Min Act: -0.0000

Data Index: 458278 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.1119. Min Act: -0.0000

Data Index: 816088 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.0984. Min Act: -0.0000

Data Index: 1326585 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.0562. Min Act: -0.0000

Data Index: 72071 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 2.8146. Min Range: -2.8146

Max Act: 1.9235. Min Act: -0.0000

Data Index: 1329064 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.0315. Min Act: -0.0000

Data Index: 277162 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.1221. Min Act: -0.0000

Data Index: 943593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.0066. Min Act: -0.0000

Data Index: 1143801 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.1174. Min Act: -0.0000

Data Index: 988503 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.1158. Min Act: -0.0000

Data Index: 478895 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.2293. Min Act: -0.0000

Data Index: 1320820 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 2.8146. Min Range: -2.8146

Max Act: 2.2144. Min Act: -0.0000

Data Index: 815867 (C4 (Web Text))

Max Activating Token Index: 592