Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1581 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0492. Min Act: -0.0003

Data Index: 497534 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0466. Min Act: -0.0003

Data Index: 154837 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0386. Min Act: -0.0003

Data Index: 468235 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1304258 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0371. Min Act: -0.0003

Data Index: 965130 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0371. Min Act: -0.0003

Data Index: 608858 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0363. Min Act: -0.0003

Data Index: 703454 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0362. Min Act: -0.0002

Data Index: 838260 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0367. Min Act: -0.0003

Data Index: 847372 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0364. Min Act: -0.0003

Data Index: 784790 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0355. Min Act: -0.0003

Data Index: 524675 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0346. Min Act: -0.0003

Data Index: 329337 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1264442 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0344. Min Act: -0.0003

Data Index: 408715 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1410162 (Python Code)

Max Activating Token Index: 126

Text #15

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1601049 (Python Code)

Max Activating Token Index: 262

Text #16

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0333. Min Act: -0.0003

Data Index: 884 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0337. Min Act: -0.0003

Data Index: 909467 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1080940 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0335. Min Act: -0.0003

Data Index: 758376 (C4 (Web Text))

Max Activating Token Index: 780