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

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

Neuron 1907 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.7261. Min Act: -0.0001

Data Index: 343796 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8686. Min Act: -0.0001

Data Index: 338228 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8298. Min Act: -0.0001

Data Index: 542863 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.6883. Min Act: -0.0001

Data Index: 720951 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9889. Min Act: -0.0001

Data Index: 578466 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8122. Min Act: -0.0001

Data Index: 539662 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.2861. Min Act: -0.0001

Data Index: 547510 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.5781. Min Act: -0.0001

Data Index: 441027 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.7181. Min Act: -0.0001

Data Index: 1156919 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.5509. Min Act: -0.0001

Data Index: 694177 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8581. Min Act: -0.0001

Data Index: 815566 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.7161. Min Act: -0.0001

Data Index: 241250 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.6957. Min Act: -0.0001

Data Index: 1313471 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.3787. Min Act: -0.0001

Data Index: 302051 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.7012. Min Act: -0.0001

Data Index: 457656 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.7007. Min Act: -0.0001

Data Index: 986852 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.7067. Min Act: -0.0001

Data Index: 169300 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8096. Min Act: -0.0001

Data Index: 629251 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.5151. Min Act: -0.0001

Data Index: 758230 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8100. Min Act: -0.0001

Data Index: 817464 (C4 (Web Text))

Max Activating Token Index: 670