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

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

Neuron 3561 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0002

Data Index: 35464 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1018406 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0454. Min Act: -0.0002

Data Index: 578667 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0442. Min Act: -0.0002

Data Index: 159199 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0436. Min Act: -0.0002

Data Index: 35741 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1136177 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0440. Min Act: -0.0002

Data Index: 594305 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0439. Min Act: -0.0002

Data Index: 261008 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1126700 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0429. Min Act: -0.0002

Data Index: 563994 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0435. Min Act: -0.0002

Data Index: 238014 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0435. Min Act: -0.0002

Data Index: 47836 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0435. Min Act: -0.0002

Data Index: 459426 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1241382 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1012763 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0442. Min Act: -0.0002

Data Index: 197691 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0440. Min Act: -0.0002

Data Index: 719984 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0432. Min Act: -0.0002

Data Index: 162510 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0431. Min Act: -0.0002

Data Index: 288716 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0430. Min Act: -0.0002

Data Index: 792806 (C4 (Web Text))

Max Activating Token Index: 122