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

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

Neuron 3826 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0966. Min Range: -1.0966

Max Act: 1.0966. Min Act: -0.0001

Data Index: 60141 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 1.0966. Min Range: -1.0966

Max Act: 1.0906. Min Act: -0.0000

Data Index: 504133 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1322557 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.9429. Min Act: -0.0001

Data Index: 190751 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.9693. Min Act: -0.0001

Data Index: 967267 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.9345. Min Act: -0.0001

Data Index: 1141808 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.9274. Min Act: -0.0001

Data Index: 1132615 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.8934. Min Act: -0.0001

Data Index: 1199716 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1145727 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.9007. Min Act: -0.0001

Data Index: 755457 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.9229. Min Act: -0.0000

Data Index: 505959 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1114897 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1152152 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.9091. Min Act: -0.0001

Data Index: 1239361 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.8481. Min Act: -0.0001

Data Index: 470389 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.8467. Min Act: -0.0001

Data Index: 554982 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.8381. Min Act: -0.0000

Data Index: 265148 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.8666. Min Act: -0.0001

Data Index: 352545 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.8130. Min Act: -0.0001

Data Index: 159429 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 1.0966. Min Range: -1.0966

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1071353 (C4 (Web Text))

Max Activating Token Index: 533