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

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

Neuron 4203 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: 3.2250. Min Range: -3.2250

Max Act: 3.2250. Min Act: 0.0000

Data Index: 252076 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.7525. Min Act: -0.0000

Data Index: 782615 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.5646. Min Act: -0.0000

Data Index: 995368 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1050849 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.4842. Min Act: -0.0000

Data Index: 74019 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.4055. Min Act: -0.0000

Data Index: 250940 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1182702 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.3597. Min Act: -0.0000

Data Index: 851064 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.3605. Min Act: -0.0000

Data Index: 708051 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.3096. Min Act: -0.0000

Data Index: 996750 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.3256. Min Act: 0.0000

Data Index: 1108049 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.3040. Min Act: -0.0000

Data Index: 1333271 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.3342. Min Act: -0.0000

Data Index: 514900 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.1455. Min Act: -0.0000

Data Index: 966153 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.4065. Min Act: -0.0000

Data Index: 187841 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.3288. Min Act: -0.0000

Data Index: 522163 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.2973. Min Act: -0.0000

Data Index: 829422 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.2074. Min Act: -0.0000

Data Index: 912356 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.2786. Min Act: -0.0000

Data Index: 770612 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 3.2250. Min Range: -3.2250

Max Act: 1.2459. Min Act: -0.0000

Data Index: 315670 (C4 (Web Text))

Max Activating Token Index: 475