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

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

Neuron 3180 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7975. Min Act: -0.0000

Data Index: 710916 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7708. Min Act: -0.0000

Data Index: 835017 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.8166. Min Act: -0.0000

Data Index: 162449 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7639. Min Act: -0.0000

Data Index: 868447 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1254571 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6710. Min Act: -0.0000

Data Index: 131617 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7297. Min Act: -0.0000

Data Index: 305163 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7006. Min Act: -0.0000

Data Index: 441689 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1341264 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6885. Min Act: -0.0000

Data Index: 243579 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7133. Min Act: -0.0000

Data Index: 670333 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7089. Min Act: -0.0000

Data Index: 35214 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7068. Min Act: -0.0000

Data Index: 13133 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6782. Min Act: -0.0000

Data Index: 855303 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1086487 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6691. Min Act: -0.0000

Data Index: 468118 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1310412 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1092021 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1352435 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6370. Min Act: -0.0000

Data Index: 83276 (C4 (Web Text))

Max Activating Token Index: 441