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

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

Neuron 3290 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1656096 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.3922. Min Act: -0.0001

Data Index: 525263 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.3630. Min Act: -0.0001

Data Index: 257287 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.3523. Min Act: -0.0001

Data Index: 134138 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.3229. Min Act: -0.0001

Data Index: 147422 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.3240. Min Act: -0.0001

Data Index: 1045619 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.3127. Min Act: -0.0001

Data Index: 1175303 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.2888. Min Act: -0.0001

Data Index: 396732 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.3089. Min Act: -0.0001

Data Index: 899985 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.2919. Min Act: -0.0001

Data Index: 1123960 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.3003. Min Act: -0.0001

Data Index: 982461 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.3097. Min Act: -0.0001

Data Index: 885774 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.2987. Min Act: -0.0001

Data Index: 701313 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.3061. Min Act: -0.0001

Data Index: 1166552 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.3024. Min Act: -0.0001

Data Index: 163755 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.2937. Min Act: -0.0001

Data Index: 327654 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1320856 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.2839. Min Act: -0.0001

Data Index: 911001 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.2833. Min Act: -0.0001

Data Index: 27812 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.4283. Min Range: -0.4283

Max Act: 0.2821. Min Act: -0.0001

Data Index: 658788 (C4 (Web Text))

Max Activating Token Index: 801