Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1560 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3767. Min Act: -0.0001

Data Index: 953412 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3086. Min Act: -0.0001

Data Index: 636851 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3114. Min Act: -0.0001

Data Index: 411498 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3038. Min Act: -0.0001

Data Index: 1232153 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3133. Min Act: -0.0001

Data Index: 262595 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2942. Min Act: -0.0001

Data Index: 36202 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3028. Min Act: -0.0001

Data Index: 1339658 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3081. Min Act: -0.0001

Data Index: 479538 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2907. Min Act: -0.0001

Data Index: 1021693 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3073. Min Act: -0.0001

Data Index: 600108 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1203558 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2789. Min Act: -0.0001

Data Index: 59014 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2750. Min Act: -0.0001

Data Index: 645412 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2851. Min Act: -0.0001

Data Index: 1091881 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2868. Min Act: -0.0001

Data Index: 999935 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1008708 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2933. Min Act: -0.0001

Data Index: 778850 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2772. Min Act: -0.0001

Data Index: 285756 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2928. Min Act: -0.0001

Data Index: 396782 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2916. Min Act: -0.0001

Data Index: 391732 (C4 (Web Text))

Max Activating Token Index: 770