Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1212 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0501. Min Act: -0.0006

Data Index: 610299 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0470. Min Act: -0.0006

Data Index: 1193602 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0444. Min Act: -0.0006

Data Index: 868219 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0443. Min Act: -0.0006

Data Index: 116798 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0405. Min Act: -0.0006

Data Index: 979669 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0413. Min Act: -0.0006

Data Index: 185237 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0400. Min Act: -0.0006

Data Index: 219823 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0424. Min Act: -0.0006

Data Index: 839072 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0414. Min Act: -0.0006

Data Index: 1452134 (Python Code)

Max Activating Token Index: 573

Text #9

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0404. Min Act: -0.0006

Data Index: 1201307 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0419. Min Act: -0.0006

Data Index: 1171467 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0400. Min Act: -0.0006

Data Index: 1071439 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0401. Min Act: -0.0006

Data Index: 969101 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0381. Min Act: -0.0006

Data Index: 1017224 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0406. Min Act: -0.0006

Data Index: 918339 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0372. Min Act: -0.0006

Data Index: 655971 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0412. Min Act: -0.0006

Data Index: 845758 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0386. Min Act: -0.0006

Data Index: 3669 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0404. Min Act: -0.0006

Data Index: 67876 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0394. Min Act: -0.0006

Data Index: 656670 (C4 (Web Text))

Max Activating Token Index: 212