Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1615 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.5168. Min Act: -0.0000

Data Index: 252507 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.3307. Min Act: -0.0000

Data Index: 511744 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0627. Min Act: -0.0000

Data Index: 767798 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0166. Min Act: -0.0000

Data Index: 420164 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0075. Min Act: -0.0000

Data Index: 117156 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0410. Min Act: -0.0000

Data Index: 281793 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1250311 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9721. Min Act: -0.0000

Data Index: 789070 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9417. Min Act: -0.0000

Data Index: 751653 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1348297 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9378. Min Act: -0.0000

Data Index: 307878 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9356. Min Act: -0.0000

Data Index: 638957 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.8397. Min Act: -0.0000

Data Index: 624397 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0125. Min Act: -0.0000

Data Index: 1242328 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.8613. Min Act: -0.0000

Data Index: 146206 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1230932 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1032805 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1133191 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1326569 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.8153. Min Act: -0.0000

Data Index: 862206 (C4 (Web Text))

Max Activating Token Index: 584