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

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

Neuron 3583 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0094. Min Range: -1.0094

Max Act: 1.0094. Min Act: -0.0001

Data Index: 774381 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9366. Min Act: -0.0001

Data Index: 479531 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9337. Min Act: -0.0001

Data Index: 242885 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9049. Min Act: -0.0001

Data Index: 918203 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9158. Min Act: -0.0001

Data Index: 754794 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8761. Min Act: -0.0001

Data Index: 404402 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7885. Min Act: -0.0001

Data Index: 713860 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9000. Min Act: -0.0001

Data Index: 842589 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8960. Min Act: -0.0001

Data Index: 871520 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8091. Min Act: -0.0001

Data Index: 663013 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7460. Min Act: -0.0001

Data Index: 278328 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8822. Min Act: -0.0001

Data Index: 374790 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7215. Min Act: -0.0001

Data Index: 344550 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.6968. Min Act: -0.0001

Data Index: 75942 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7656. Min Act: -0.0001

Data Index: 1037615 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7557. Min Act: -0.0001

Data Index: 235825 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7494. Min Act: -0.0001

Data Index: 1100059 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.6974. Min Act: -0.0001

Data Index: 1016079 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7600. Min Act: -0.0001

Data Index: 1072366 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7193. Min Act: -0.0001

Data Index: 712599 (C4 (Web Text))

Max Activating Token Index: 693