Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2727 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1324390 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0535. Min Act: -0.0001

Data Index: 192378 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0508. Min Act: -0.0001

Data Index: 28984 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0501. Min Act: -0.0001

Data Index: 673376 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0493. Min Act: -0.0001

Data Index: 639565 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0500. Min Act: -0.0001

Data Index: 826973 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0491. Min Act: -0.0001

Data Index: 1341287 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0465. Min Act: -0.0001

Data Index: 47644 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0468. Min Act: -0.0001

Data Index: 558776 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0450. Min Act: -0.0001

Data Index: 196089 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0455. Min Act: -0.0001

Data Index: 398778 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0454. Min Act: -0.0001

Data Index: 453438 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1319486 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0458. Min Act: -0.0001

Data Index: 144341 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0446. Min Act: -0.0001

Data Index: 675820 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0437. Min Act: -0.0001

Data Index: 837179 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0442. Min Act: -0.0001

Data Index: 459391 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0429. Min Act: -0.0001

Data Index: 105585 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0440. Min Act: -0.0001

Data Index: 233854 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0435. Min Act: -0.0001

Data Index: 275612 (C4 (Web Text))

Max Activating Token Index: 994