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

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

Neuron 231 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.9930. Min Act: -0.0001

Data Index: 566740 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.9035. Min Act: -0.0001

Data Index: 429445 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 1.0199. Min Range: -1.0199

Max Act: 1.0199. Min Act: -0.0001

Data Index: 809473 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.8757. Min Act: -0.0001

Data Index: 239291 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.7899. Min Act: -0.0001

Data Index: 938483 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.8380. Min Act: -0.0001

Data Index: 584198 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.8661. Min Act: -0.0001

Data Index: 1301764 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.8203. Min Act: -0.0001

Data Index: 430047 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.8771. Min Act: -0.0001

Data Index: 610669 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.7188. Min Act: -0.0001

Data Index: 358946 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.8126. Min Act: -0.0001

Data Index: 556081 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.8202. Min Act: -0.0001

Data Index: 461298 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.7992. Min Act: -0.0001

Data Index: 130952 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.7914. Min Act: -0.0001

Data Index: 34469 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.7189. Min Act: -0.0001

Data Index: 1045614 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.7656. Min Act: -0.0001

Data Index: 533679 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.7871. Min Act: -0.0001

Data Index: 482107 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.6787. Min Act: -0.0001

Data Index: 338030 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.7489. Min Act: -0.0001

Data Index: 154655 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 1.0199. Min Range: -1.0199

Max Act: 0.7848. Min Act: -0.0001

Data Index: 1298782 (C4 (Web Text))

Max Activating Token Index: 795