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

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

Neuron 483 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: 0.3740. Min Range: -0.3740

Max Act: 0.3740. Min Act: -0.0002

Data Index: 390829 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3366. Min Act: -0.0002

Data Index: 751755 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3057. Min Act: -0.0002

Data Index: 1268985 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3158. Min Act: -0.0002

Data Index: 818027 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3206. Min Act: -0.0002

Data Index: 734398 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3185. Min Act: -0.0002

Data Index: 522660 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3041. Min Act: -0.0002

Data Index: 1344221 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3144. Min Act: -0.0002

Data Index: 1143745 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3193. Min Act: -0.0002

Data Index: 956064 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2963. Min Act: -0.0002

Data Index: 1284776 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3018. Min Act: -0.0002

Data Index: 353869 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2990. Min Act: -0.0002

Data Index: 1110735 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2849. Min Act: -0.0002

Data Index: 748567 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2694. Min Act: -0.0002

Data Index: 123575 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2819. Min Act: -0.0002

Data Index: 338758 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2743. Min Act: -0.0002

Data Index: 16766 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2718. Min Act: -0.0002

Data Index: 61564 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2352. Min Act: -0.0002

Data Index: 1216931 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2738. Min Act: -0.0002

Data Index: 299812 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2560. Min Act: -0.0002

Data Index: 1078289 (C4 (Web Text))

Max Activating Token Index: 68