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

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

Neuron 2335 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.8083. Min Act: -0.0002

Data Index: 788447 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7946. Min Act: -0.0002

Data Index: 827098 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6923. Min Act: -0.0002

Data Index: 248541 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6817. Min Act: -0.0002

Data Index: 961565 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7532. Min Act: -0.0002

Data Index: 826880 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6553. Min Act: -0.0001

Data Index: 995241 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6496. Min Act: -0.0001

Data Index: 1349795 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6648. Min Act: -0.0001

Data Index: 1383100 (Python Code)

Max Activating Token Index: 229

Text #8

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5993. Min Act: -0.0001

Data Index: 1498603 (Python Code)

Max Activating Token Index: 620

Text #9

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6364. Min Act: -0.0002

Data Index: 1336849 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6000. Min Act: -0.0002

Data Index: 331807 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6019. Min Act: -0.0001

Data Index: 241260 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1534268 (Python Code)

Max Activating Token Index: 65

Text #13

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5831. Min Act: -0.0001

Data Index: 1054859 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5945. Min Act: -0.0002

Data Index: 163565 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5766. Min Act: -0.0002

Data Index: 796580 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5530. Min Act: -0.0002

Data Index: 1306168 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5331. Min Act: -0.0002

Data Index: 1057813 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5087. Min Act: -0.0002

Data Index: 1039998 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6013. Min Act: -0.0001

Data Index: 1161349 (C4 (Web Text))

Max Activating Token Index: 866