Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 28 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.9803. Min Act: -0.0001

Data Index: 1246019 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.8436. Min Act: -0.0001

Data Index: 227706 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.7189. Min Act: -0.0001

Data Index: 1234223 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.8096. Min Act: -0.0001

Data Index: 1348844 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.6962. Min Act: -0.0001

Data Index: 410752 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.6825. Min Act: -0.0001

Data Index: 559463 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.6788. Min Act: -0.0001

Data Index: 1265577 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.6218. Min Act: -0.0001

Data Index: 906049 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.5438. Min Act: -0.0001

Data Index: 975700 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.5786. Min Act: -0.0001

Data Index: 1119807 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.6065. Min Act: -0.0001

Data Index: 371892 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.5229. Min Act: -0.0001

Data Index: 1069664 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.4715. Min Act: -0.0001

Data Index: 797265 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.4965. Min Act: -0.0001

Data Index: 1199517 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.3745. Min Act: -0.0001

Data Index: 342947 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.3887. Min Act: -0.0001

Data Index: 1208343 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.4967. Min Act: -0.0001

Data Index: 832146 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.4486. Min Act: -0.0001

Data Index: 1002316 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.4434. Min Act: -0.0001

Data Index: 414552 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.3944. Min Act: -0.0001

Data Index: 276164 (C4 (Web Text))

Max Activating Token Index: 48