Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4441 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.5844. Min Act: -0.0000

Data Index: 2240 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.6045. Min Act: -0.0000

Data Index: 570000 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.6451. Min Act: -0.0000

Data Index: 298593 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.5960. Min Act: -0.0000

Data Index: 794267 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1197044 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.5384. Min Act: -0.0000

Data Index: 996188 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1153096 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.5782. Min Act: -0.0000

Data Index: 392997 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1043730 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.4731. Min Act: -0.0001

Data Index: 262234 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.4917. Min Act: -0.0000

Data Index: 642259 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.4911. Min Act: -0.0000

Data Index: 806722 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1206066 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.4514. Min Act: -0.0000

Data Index: 982429 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.4004. Min Act: -0.0000

Data Index: 83892 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.4155. Min Act: -0.0000

Data Index: 956931 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.4979. Min Act: -0.0000

Data Index: 458153 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.4404. Min Act: -0.0001

Data Index: 328559 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.4156. Min Act: -0.0001

Data Index: 1286625 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.6451. Min Range: -0.6451

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1201813 (C4 (Web Text))

Max Activating Token Index: 431