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

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

Neuron 418 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.8194. Min Act: -0.0000

Data Index: 982288 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7484. Min Act: -0.0000

Data Index: 497478 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.6738. Min Act: -0.0000

Data Index: 939126 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.6669. Min Act: -0.0000

Data Index: 539956 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.6424. Min Act: -0.0000

Data Index: 411246 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1239095 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.5818. Min Act: -0.0000

Data Index: 93412 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.6102. Min Act: -0.0000

Data Index: 796070 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.5192. Min Act: -0.0000

Data Index: 541029 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.5419. Min Act: -0.0000

Data Index: 817275 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.5391. Min Act: -0.0000

Data Index: 449333 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.5258. Min Act: -0.0000

Data Index: 78387 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1232841 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.5155. Min Act: -0.0000

Data Index: 549166 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.4858. Min Act: -0.0000

Data Index: 517558 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.4939. Min Act: -0.0000

Data Index: 334460 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1206730 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.4696. Min Act: -0.0000

Data Index: 398802 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.4818. Min Act: -0.0000

Data Index: 980327 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.4854. Min Act: -0.0000

Data Index: 555469 (C4 (Web Text))

Max Activating Token Index: 694