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

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

Neuron 3821 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: 0.8580. Min Range: -0.8580

Max Act: 0.8580. Min Act: -0.0001

Data Index: 396871 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.8064. Min Act: -0.0001

Data Index: 506951 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7970. Min Act: -0.0000

Data Index: 285823 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7520. Min Act: -0.0001

Data Index: 588375 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7693. Min Act: -0.0000

Data Index: 727889 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7575. Min Act: -0.0000

Data Index: 877959 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1323902 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.8441. Min Act: -0.0001

Data Index: 227843 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7113. Min Act: -0.0001

Data Index: 482820 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7344. Min Act: -0.0000

Data Index: 877382 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6695. Min Act: -0.0001

Data Index: 882632 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7119. Min Act: -0.0000

Data Index: 879471 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6880. Min Act: -0.0001

Data Index: 911961 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1219500 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6531. Min Act: -0.0001

Data Index: 1035205 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6458. Min Act: -0.0000

Data Index: 307552 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6667. Min Act: -0.0000

Data Index: 480988 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6470. Min Act: -0.0001

Data Index: 570694 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1176097 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6800. Min Act: -0.0000

Data Index: 38228 (C4 (Web Text))

Max Activating Token Index: 388