Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4920 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1095225 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1314837 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6816. Min Act: -0.0000

Data Index: 140582 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6954. Min Act: -0.0000

Data Index: 618562 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1120065 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6656. Min Act: 0.0000

Data Index: 931416 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6514. Min Act: 0.0000

Data Index: 397352 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6399. Min Act: -0.0000

Data Index: 682186 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1051551 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6043. Min Act: -0.0000

Data Index: 239225 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1293137 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5927. Min Act: -0.0000

Data Index: 980241 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6163. Min Act: -0.0000

Data Index: 158991 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1240345 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5905. Min Act: -0.0000

Data Index: 863304 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5681. Min Act: -0.0000

Data Index: 947636 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6039. Min Act: -0.0000

Data Index: 262902 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5899. Min Act: -0.0000

Data Index: 257911 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5662. Min Act: 0.0001

Data Index: 981245 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5952. Min Act: -0.0000

Data Index: 366352 (C4 (Web Text))

Max Activating Token Index: 389