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

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

Neuron 3660 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6249. Min Act: -0.0000

Data Index: 224232 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5799. Min Act: -0.0001

Data Index: 889656 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1094101 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5056. Min Act: -0.0000

Data Index: 791137 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4774. Min Act: -0.0000

Data Index: 966185 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4745. Min Act: -0.0000

Data Index: 663239 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4679. Min Act: -0.0000

Data Index: 556772 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4903. Min Act: -0.0000

Data Index: 481538 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4502. Min Act: -0.0000

Data Index: 450843 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4428. Min Act: -0.0000

Data Index: 49842 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.3972. Min Act: -0.0000

Data Index: 917829 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4198. Min Act: -0.0001

Data Index: 828288 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4310. Min Act: -0.0000

Data Index: 430991 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4281. Min Act: -0.0000

Data Index: 10727 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4276. Min Act: -0.0000

Data Index: 391633 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4241. Min Act: -0.0001

Data Index: 1359040 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4433. Min Act: -0.0001

Data Index: 355957 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4125. Min Act: -0.0000

Data Index: 243736 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.3801. Min Act: -0.0000

Data Index: 439308 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1306035 (C4 (Web Text))

Max Activating Token Index: 573