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

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

Neuron 4251 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.2902. Min Act: -0.0001

Data Index: 1115656 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.1382. Min Act: -0.0001

Data Index: 239497 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.0549. Min Act: -0.0001

Data Index: 948614 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.2902. Min Range: -1.2902

Max Act: 0.8065. Min Act: -0.0001

Data Index: 1207778 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.1229. Min Act: -0.0001

Data Index: 21108 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.0859. Min Act: -0.0001

Data Index: 1017584 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.0590. Min Act: -0.0001

Data Index: 321315 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.0143. Min Act: -0.0001

Data Index: 1346829 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.0111. Min Act: -0.0001

Data Index: 415620 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 1.2902. Min Range: -1.2902

Max Act: 0.9265. Min Act: -0.0000

Data Index: 183378 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 1.2902. Min Range: -1.2902

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1229827 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.2902. Min Range: -1.2902

Max Act: 0.9473. Min Act: -0.0001

Data Index: 1190401 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.0024. Min Act: -0.0001

Data Index: 917463 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.0227. Min Act: -0.0001

Data Index: 564104 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 1.2902. Min Range: -1.2902

Max Act: 0.9254. Min Act: -0.0001

Data Index: 708887 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.0030. Min Act: -0.0001

Data Index: 811796 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.0259. Min Act: -0.0001

Data Index: 795336 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.2902. Min Range: -1.2902

Max Act: 0.8885. Min Act: -0.0001

Data Index: 209221 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.1119. Min Act: -0.0001

Data Index: 1204281 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 1.2902. Min Range: -1.2902

Max Act: 1.0485. Min Act: -0.0001

Data Index: 1617 (C4 (Web Text))

Max Activating Token Index: 48