Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 169 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1007532 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1096790 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0079. Min Act: -0.0006

Data Index: 556811 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 87095 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0065. Min Act: -0.0006

Data Index: 422316 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0006

Data Index: 649073 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0071. Min Act: -0.0006

Data Index: 531146 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0068. Min Act: -0.0006

Data Index: 783918 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0062. Min Act: -0.0006

Data Index: 989102 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1218926 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1337956 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0066. Min Act: -0.0006

Data Index: 459870 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0064. Min Act: -0.0006

Data Index: 445867 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0069. Min Act: -0.0006

Data Index: 813523 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0066. Min Act: -0.0006

Data Index: 810949 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0061. Min Act: -0.0006

Data Index: 862976 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0064. Min Act: -0.0006

Data Index: 287580 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0064. Min Act: -0.0006

Data Index: 584198 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0062. Min Act: -0.0006

Data Index: 174501 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0058. Min Act: -0.0006

Data Index: 602607 (C4 (Web Text))

Max Activating Token Index: 322