Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3622 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.7496. Min Act: -0.0001

Data Index: 828850 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.7509. Min Act: -0.0001

Data Index: 1212948 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.7283. Min Act: -0.0000

Data Index: 524646 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.7138. Min Act: -0.0000

Data Index: 346847 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6377. Min Act: -0.0000

Data Index: 979483 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6543. Min Act: -0.0001

Data Index: 523310 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1287648 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1320043 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6115. Min Act: -0.0000

Data Index: 119161 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6065. Min Act: -0.0001

Data Index: 812774 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6040. Min Act: -0.0000

Data Index: 679303 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6015. Min Act: -0.0001

Data Index: 1248204 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1137806 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5834. Min Act: -0.0001

Data Index: 20108 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5802. Min Act: -0.0000

Data Index: 278088 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6166. Min Act: -0.0000

Data Index: 80774 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5937. Min Act: -0.0001

Data Index: 662364 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5915. Min Act: -0.0000

Data Index: 423223 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5759. Min Act: -0.0000

Data Index: 700137 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6114. Min Act: -0.0000

Data Index: 198418 (C4 (Web Text))

Max Activating Token Index: 621