Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1122 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.7989. Min Act: -0.0001

Data Index: 1113154 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.5072. Min Act: -0.0001

Data Index: 715371 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.5686. Min Act: -0.0001

Data Index: 1152524 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3278. Min Act: -0.0001

Data Index: 1181406 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.4136. Min Act: -0.0001

Data Index: 41165 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3419. Min Act: -0.0001

Data Index: 830773 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3154. Min Act: -0.0001

Data Index: 1325196 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3774. Min Act: -0.0001

Data Index: 1037417 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.4795. Min Act: -0.0001

Data Index: 1128424 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3814. Min Act: -0.0001

Data Index: 170455 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3914. Min Act: -0.0001

Data Index: 335129 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.1696. Min Act: -0.0001

Data Index: 513071 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.2662. Min Act: -0.0001

Data Index: 25560 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3228. Min Act: -0.0001

Data Index: 319464 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3237. Min Act: -0.0001

Data Index: 1009399 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3559. Min Act: -0.0001

Data Index: 206317 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.4679. Min Act: -0.0001

Data Index: 516025 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3912. Min Act: -0.0001

Data Index: 152749 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3996. Min Act: -0.0001

Data Index: 1285113 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 1.7989. Min Range: -1.7989

Max Act: 1.3140. Min Act: -0.0001

Data Index: 454869 (C4 (Web Text))

Max Activating Token Index: 613