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

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

Neuron 3375 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9851. Min Range: -4.9851

Max Act: 4.9851. Min Act: -0.0000

Data Index: 659944 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 4.9851. Min Range: -4.9851

Max Act: 4.8796. Min Act: -0.0000

Data Index: 561781 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 4.9851. Min Range: -4.9851

Max Act: 4.8207. Min Act: -0.0000

Data Index: 30693 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.9139. Min Act: -0.0000

Data Index: 1290128 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.8913. Min Act: -0.0000

Data Index: 1330114 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 4.9851. Min Range: -4.9851

Max Act: 4.0138. Min Act: -0.0000

Data Index: 1165101 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.7108. Min Act: -0.0000

Data Index: 703318 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.5062. Min Act: -0.0000

Data Index: 935823 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.4640. Min Act: -0.0000

Data Index: 327764 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.7436. Min Act: -0.0000

Data Index: 1160692 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.5286. Min Act: -0.0000

Data Index: 425804 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.3953. Min Act: -0.0000

Data Index: 1067111 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.3476. Min Act: -0.0000

Data Index: 1214826 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.3006. Min Act: -0.0000

Data Index: 119838 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.5923. Min Act: -0.0000

Data Index: 1146233 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.5649. Min Act: -0.0000

Data Index: 697756 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.8998. Min Act: -0.0000

Data Index: 78926 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.1089. Min Act: -0.0000

Data Index: 1268062 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.3970. Min Act: -0.0000

Data Index: 785845 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 4.9851. Min Range: -4.9851

Max Act: 3.2468. Min Act: -0.0000

Data Index: 991089 (C4 (Web Text))

Max Activating Token Index: 248