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

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

Neuron 3 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.7593. Min Act: -0.0000

Data Index: 1266260 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.6852. Min Act: -0.0000

Data Index: 78184 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.4107. Min Act: -0.0000

Data Index: 1253019 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.6495. Min Act: -0.0000

Data Index: 162006 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.5992. Min Act: -0.0000

Data Index: 788298 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.4183. Min Act: -0.0000

Data Index: 1033568 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2668. Min Act: -0.0000

Data Index: 970055 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2883. Min Act: -0.0000

Data Index: 945469 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2810. Min Act: -0.0000

Data Index: 868982 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1051. Min Act: -0.0000

Data Index: 703441 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2091. Min Act: -0.0000

Data Index: 985575 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1477. Min Act: -0.0000

Data Index: 570699 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1102. Min Act: -0.0000

Data Index: 1183215 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2069. Min Act: -0.0000

Data Index: 1208702 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.0874. Min Act: -0.0000

Data Index: 1158608 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1450. Min Act: -0.0000

Data Index: 690649 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.0035. Min Act: -0.0000

Data Index: 1131529 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 2.7593. Min Range: -2.7593

Max Act: 1.9989. Min Act: -0.0000

Data Index: 165854 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 2.7593. Min Range: -2.7593

Max Act: 1.9730. Min Act: -0.0000

Data Index: 16294 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 2.7593. Min Range: -2.7593

Max Act: 1.9530. Min Act: -0.0000

Data Index: 1287163 (C4 (Web Text))

Max Activating Token Index: 952