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

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

Neuron 3535 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5994. Min Range: -5.5994

Max Act: 5.4155. Min Act: -0.0001

Data Index: 1049765 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 5.5994. Min Range: -5.5994

Max Act: 5.5994. Min Act: -0.0001

Data Index: 707701 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 5.5994. Min Range: -5.5994

Max Act: 5.5498. Min Act: -0.0001

Data Index: 1230794 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.8541. Min Act: -0.0001

Data Index: 150705 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.3899. Min Act: -0.0001

Data Index: 1179523 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.7500. Min Act: -0.0001

Data Index: 123149 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.4712. Min Act: -0.0001

Data Index: 238127 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.8298. Min Act: -0.0001

Data Index: 1306135 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.4704. Min Act: -0.0001

Data Index: 380026 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.4239. Min Act: -0.0001

Data Index: 1227164 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.3687. Min Act: -0.0001

Data Index: 792763 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.3779. Min Act: -0.0001

Data Index: 830920 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.6600. Min Act: -0.0001

Data Index: 861193 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.1384. Min Act: -0.0001

Data Index: 1192095 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.4121. Min Act: -0.0001

Data Index: 111069 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.6034. Min Act: -0.0001

Data Index: 109729 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.0715. Min Act: -0.0001

Data Index: 561672 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.7252. Min Act: -0.0001

Data Index: 1217758 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.1816. Min Act: -0.0001

Data Index: 244503 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 5.5994. Min Range: -5.5994

Max Act: 4.3110. Min Act: -0.0001

Data Index: 801249 (C4 (Web Text))

Max Activating Token Index: 10