Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1411 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.7847. Min Act: -0.0002

Data Index: 833214 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.6159. Min Act: -0.0001

Data Index: 620972 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.6051. Min Act: -0.0002

Data Index: 1133834 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.6532. Min Act: -0.0001

Data Index: 695160 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.6102. Min Act: -0.0002

Data Index: 831709 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.5161. Min Act: -0.0002

Data Index: 1270242 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.5494. Min Act: -0.0002

Data Index: 889206 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.4613. Min Act: -0.0002

Data Index: 1002137 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.5464. Min Act: -0.0002

Data Index: 1191764 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.5893. Min Act: -0.0002

Data Index: 289935 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.5329. Min Act: -0.0001

Data Index: 1142900 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.5765. Min Act: -0.0002

Data Index: 1144387 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.5270. Min Act: -0.0002

Data Index: 964922 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.5131. Min Act: -0.0001

Data Index: 454827 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.5127. Min Act: -0.0002

Data Index: 838516 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.3868. Min Act: -0.0002

Data Index: 1304318 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.5034. Min Act: -0.0002

Data Index: 1016981 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.5340. Min Act: -0.0001

Data Index: 36671 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.4355. Min Act: -0.0001

Data Index: 619875 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 1.7847. Min Range: -1.7847

Max Act: 1.4767. Min Act: -0.0002

Data Index: 876836 (C4 (Web Text))

Max Activating Token Index: 43