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

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

Neuron 3753 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.4635. Min Act: -0.0000

Data Index: 1097223 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2149. Min Act: -0.0000

Data Index: 791621 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2870. Min Act: -0.0000

Data Index: 744213 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1847. Min Act: -0.0001

Data Index: 650795 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1092. Min Act: -0.0001

Data Index: 1043236 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0814. Min Act: -0.0000

Data Index: 766485 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1314656 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0329. Min Act: -0.0000

Data Index: 1191429 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.9015. Min Act: -0.0000

Data Index: 718442 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.9005. Min Act: -0.0001

Data Index: 935019 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1040240 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.8872. Min Act: -0.0001

Data Index: 1471234 (Python Code)

Max Activating Token Index: 776

Text #12

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.7450. Min Act: -0.0000

Data Index: 409883 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.7549. Min Act: -0.0000

Data Index: 371092 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.8802. Min Act: -0.0001

Data Index: 226781 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1146138 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.7972. Min Act: -0.0000

Data Index: 246228 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.7050. Min Act: -0.0001

Data Index: 779445 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.7501. Min Act: -0.0000

Data Index: 580726 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.7755. Min Act: -0.0000

Data Index: 11165 (C4 (Web Text))

Max Activating Token Index: 106