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

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

Neuron 69 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2470. Min Act: -0.0001

Data Index: 811543 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2319. Min Act: -0.0001

Data Index: 681900 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2292. Min Act: -0.0001

Data Index: 691474 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2296. Min Act: -0.0001

Data Index: 857860 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2241. Min Act: -0.0001

Data Index: 198781 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2076. Min Act: -0.0001

Data Index: 299329 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1177911 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2186. Min Act: -0.0001

Data Index: 210105 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2116. Min Act: -0.0001

Data Index: 314797 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2013. Min Act: -0.0001

Data Index: 897080 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2100. Min Act: -0.0001

Data Index: 704845 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2088. Min Act: -0.0001

Data Index: 1261780 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2143. Min Act: -0.0001

Data Index: 1202450 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1988. Min Act: -0.0001

Data Index: 813904 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2061. Min Act: -0.0001

Data Index: 831764 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2027. Min Act: -0.0001

Data Index: 1054796 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2097. Min Act: -0.0001

Data Index: 1059504 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1995. Min Act: -0.0001

Data Index: 441695 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2067. Min Act: -0.0001

Data Index: 1015533 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1003173 (C4 (Web Text))

Max Activating Token Index: 544