Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1492 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0902. Min Act: -0.0005

Data Index: 179886 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0853. Min Act: -0.0005

Data Index: 426838 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0976. Min Act: -0.0005

Data Index: 916587 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0939. Min Act: -0.0005

Data Index: 195304 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0956. Min Act: -0.0005

Data Index: 882631 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0936. Min Act: -0.0005

Data Index: 274142 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0955. Min Act: -0.0005

Data Index: 866138 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0830. Min Act: -0.0005

Data Index: 298381 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0914. Min Act: -0.0005

Data Index: 347911 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0863. Min Act: -0.0005

Data Index: 89423 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0821. Min Act: -0.0005

Data Index: 506203 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0853. Min Act: -0.0005

Data Index: 1316561 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0844. Min Act: -0.0005

Data Index: 36221 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0873. Min Act: -0.0005

Data Index: 465015 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0837. Min Act: -0.0005

Data Index: 299550 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0871. Min Act: -0.0005

Data Index: 791911 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0824. Min Act: -0.0005

Data Index: 1412666 (Python Code)

Max Activating Token Index: 479

Text #17

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0842. Min Act: -0.0005

Data Index: 955692 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0874. Min Act: -0.0005

Data Index: 203100 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0807. Min Act: -0.0005

Data Index: 973168 (C4 (Web Text))

Max Activating Token Index: 515