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

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

Neuron 3070 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: 0.3306. Min Range: -0.3306

Max Act: 0.3306. Min Act: -0.0001

Data Index: 864932 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1144242 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3067. Min Act: -0.0001

Data Index: 353434 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3132. Min Act: -0.0001

Data Index: 867606 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3080. Min Act: -0.0001

Data Index: 1056783 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3059. Min Act: -0.0001

Data Index: 545106 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3042. Min Act: -0.0001

Data Index: 727616 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2967. Min Act: -0.0001

Data Index: 592708 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2973. Min Act: -0.0001

Data Index: 365052 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3063. Min Act: -0.0001

Data Index: 1021432 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2962. Min Act: -0.0001

Data Index: 1346094 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2976. Min Act: -0.0001

Data Index: 864931 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2941. Min Act: -0.0001

Data Index: 1045215 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3055. Min Act: -0.0001

Data Index: 453519 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2851. Min Act: -0.0001

Data Index: 1086246 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2850. Min Act: -0.0001

Data Index: 1066620 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2923. Min Act: -0.0001

Data Index: 194934 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2994. Min Act: -0.0001

Data Index: 697208 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3026. Min Act: -0.0001

Data Index: 773455 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2939. Min Act: -0.0001

Data Index: 894947 (C4 (Web Text))

Max Activating Token Index: 292