Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 313 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.7441. Min Act: -0.0001

Data Index: 587140 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 3.0272. Min Range: -3.0272

Max Act: 3.0272. Min Act: -0.0001

Data Index: 1020514 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.6548. Min Act: -0.0001

Data Index: 1189319 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.8568. Min Act: -0.0001

Data Index: 995027 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.1574. Min Act: -0.0000

Data Index: 765066 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.1058. Min Act: -0.0000

Data Index: 161866 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.0785. Min Act: -0.0000

Data Index: 42460 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.0811. Min Act: -0.0000

Data Index: 887022 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.1661. Min Act: -0.0001

Data Index: 1310411 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 3.0272. Min Range: -3.0272

Max Act: 1.9639. Min Act: -0.0001

Data Index: 1146252 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.1504. Min Act: -0.0001

Data Index: 908558 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.0535. Min Act: -0.0001

Data Index: 203545 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 3.0272. Min Range: -3.0272

Max Act: 1.8174. Min Act: -0.0001

Data Index: 999136 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 3.0272. Min Range: -3.0272

Max Act: 1.9070. Min Act: -0.0001

Data Index: 227614 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 3.0272. Min Range: -3.0272

Max Act: 1.9888. Min Act: -0.0001

Data Index: 698951 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 3.0272. Min Range: -3.0272

Max Act: 1.8704. Min Act: -0.0001

Data Index: 78352 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 3.0272. Min Range: -3.0272

Max Act: 1.8784. Min Act: -0.0001

Data Index: 980391 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.1874. Min Act: -0.0000

Data Index: 895589 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 3.0272. Min Range: -3.0272

Max Act: 1.9548. Min Act: -0.0001

Data Index: 1273640 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.0728. Min Act: -0.0001

Data Index: 400082 (C4 (Web Text))

Max Activating Token Index: 673