Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 819 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4698. Min Act: -0.0006

Data Index: 516126 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4381. Min Act: -0.0006

Data Index: 882135 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4606. Min Act: -0.0006

Data Index: 693333 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4234. Min Act: -0.0006

Data Index: 1274927 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4103. Min Act: -0.0006

Data Index: 1232718 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4520. Min Act: -0.0006

Data Index: 1084436 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4086. Min Act: -0.0006

Data Index: 677122 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4058. Min Act: -0.0006

Data Index: 579948 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4187. Min Act: -0.0006

Data Index: 1085211 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4021. Min Act: -0.0006

Data Index: 386427 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4140. Min Act: -0.0006

Data Index: 657394 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3985. Min Act: -0.0006

Data Index: 542810 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3979. Min Act: -0.0006

Data Index: 853052 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4109. Min Act: -0.0006

Data Index: 1207379 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3966. Min Act: -0.0006

Data Index: 158865 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4059. Min Act: -0.0006

Data Index: 1062547 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3809. Min Act: -0.0006

Data Index: 55740 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4043. Min Act: -0.0006

Data Index: 160417 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3890. Min Act: -0.0006

Data Index: 561880 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4179. Min Act: -0.0006

Data Index: 611466 (C4 (Web Text))

Max Activating Token Index: 364