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

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

Neuron 822 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.7356. Min Act: -0.0002

Data Index: 496975 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.8124. Min Act: -0.0002

Data Index: 792945 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.8946. Min Act: -0.0002

Data Index: 1157877 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.3645. Min Act: -0.0002

Data Index: 13929 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.6395. Min Act: -0.0002

Data Index: 1106375 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.4336. Min Act: -0.0002

Data Index: 1337960 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.5237. Min Act: -0.0002

Data Index: 518840 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.3956. Min Act: -0.0002

Data Index: 822609 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.3525. Min Act: -0.0002

Data Index: 492985 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.3028. Min Act: -0.0002

Data Index: 588723 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.1716. Min Act: -0.0002

Data Index: 557 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.4885. Min Act: -0.0002

Data Index: 240804 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2018. Min Act: -0.0002

Data Index: 1080509 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2882. Min Act: -0.0002

Data Index: 61835 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2525. Min Act: -0.0002

Data Index: 1343216 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.1288. Min Act: -0.0002

Data Index: 809063 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2120. Min Act: -0.0002

Data Index: 474609 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2107. Min Act: -0.0002

Data Index: 860443 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.1052. Min Act: -0.0002

Data Index: 428476 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.1637. Min Act: -0.0002

Data Index: 755989 (C4 (Web Text))

Max Activating Token Index: 4