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

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

Neuron 3585 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1102107 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1182. Min Act: -0.0001

Data Index: 1125269 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1062. Min Act: -0.0001

Data Index: 540487 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1238279 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1114. Min Act: -0.0001

Data Index: 516960 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1141. Min Act: -0.0001

Data Index: 602755 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1099. Min Act: -0.0001

Data Index: 240689 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1169797 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1050420 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0987. Min Act: -0.0001

Data Index: 624975 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1280309 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1258449 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0993. Min Act: -0.0001

Data Index: 216839 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0967. Min Act: -0.0000

Data Index: 255558 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1042. Min Act: -0.0001

Data Index: 478107 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0941. Min Act: -0.0001

Data Index: 537736 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0967. Min Act: -0.0001

Data Index: 348299 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0930. Min Act: -0.0001

Data Index: 749245 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1326783 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.0964. Min Act: -0.0001

Data Index: 995268 (C4 (Web Text))

Max Activating Token Index: 749