Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2703 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9752. Min Act: -0.0001

Data Index: 917989 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9492. Min Act: -0.0001

Data Index: 404476 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8309. Min Act: -0.0001

Data Index: 1255269 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8486. Min Act: -0.0001

Data Index: 138848 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8421. Min Act: -0.0001

Data Index: 81832 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7930. Min Act: -0.0001

Data Index: 739520 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8418. Min Act: -0.0001

Data Index: 1292835 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8035. Min Act: -0.0001

Data Index: 484575 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7922. Min Act: -0.0001

Data Index: 552702 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7292. Min Act: -0.0001

Data Index: 23701 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7197. Min Act: -0.0001

Data Index: 133554 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7947. Min Act: -0.0001

Data Index: 304881 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7290. Min Act: -0.0001

Data Index: 97404 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7475. Min Act: -0.0001

Data Index: 436045 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7284. Min Act: -0.0001

Data Index: 1342191 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.6815. Min Act: -0.0001

Data Index: 1219819 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7154. Min Act: -0.0001

Data Index: 937487 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7176. Min Act: -0.0001

Data Index: 3250 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7079. Min Act: -0.0001

Data Index: 1292084 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7050. Min Act: -0.0001

Data Index: 24206 (C4 (Web Text))

Max Activating Token Index: 472