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

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

Neuron 2249 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4552. Min Act: -0.0000

Data Index: 838569 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3986. Min Act: -0.0000

Data Index: 40925 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3996. Min Act: -0.0000

Data Index: 974149 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4127. Min Act: -0.0000

Data Index: 29306 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4165. Min Act: -0.0000

Data Index: 298283 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4148. Min Act: -0.0000

Data Index: 620016 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1001359 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1012388 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3820. Min Act: -0.0000

Data Index: 589166 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1276401 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1318377 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3862. Min Act: -0.0000

Data Index: 551068 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4015. Min Act: -0.0000

Data Index: 23316 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3936. Min Act: -0.0000

Data Index: 599245 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3671. Min Act: -0.0000

Data Index: 490697 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3649. Min Act: -0.0000

Data Index: 140284 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3781. Min Act: -0.0000

Data Index: 378580 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1051074 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3531. Min Act: -0.0000

Data Index: 205584 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4025. Min Act: -0.0000

Data Index: 182265 (C4 (Web Text))

Max Activating Token Index: 572