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

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

Neuron 3703 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3209. Min Range: -1.3209

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1285362 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.3209. Min Range: -1.3209

Max Act: 1.0847. Min Act: -0.0000

Data Index: 462112 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 1.3209. Min Range: -1.3209

Max Act: 1.1975. Min Act: -0.0000

Data Index: 444896 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.3209. Min Range: -1.3209

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1004597 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.3209. Min Range: -1.3209

Max Act: 1.0034. Min Act: -0.0000

Data Index: 617008 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.3209. Min Range: -1.3209

Max Act: 1.0643. Min Act: -0.0000

Data Index: 287860 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 1.3209. Min Range: -1.3209

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1226833 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1027029 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1124179 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.9476. Min Act: -0.0000

Data Index: 55647 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.9439. Min Act: -0.0000

Data Index: 169317 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.9444. Min Act: -0.0000

Data Index: 919660 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1202361 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.9147. Min Act: -0.0000

Data Index: 439250 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.8998. Min Act: -0.0000

Data Index: 151913 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1055222 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.9282. Min Act: -0.0000

Data Index: 34245 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.8706. Min Act: -0.0000

Data Index: 97127 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.9029. Min Act: -0.0000

Data Index: 763336 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.8478. Min Act: 0.0000

Data Index: 860176 (C4 (Web Text))

Max Activating Token Index: 342