Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1504 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.5016. Min Act: -0.0004

Data Index: 1109955 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4641. Min Act: -0.0004

Data Index: 1307037 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4477. Min Act: -0.0004

Data Index: 961714 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4317. Min Act: -0.0004

Data Index: 1133765 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4288. Min Act: -0.0004

Data Index: 257810 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4268. Min Act: -0.0004

Data Index: 819194 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4411. Min Act: -0.0004

Data Index: 906399 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4249. Min Act: -0.0004

Data Index: 434925 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4135. Min Act: -0.0004

Data Index: 938463 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4109. Min Act: -0.0004

Data Index: 1066074 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4097. Min Act: -0.0004

Data Index: 888313 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4077. Min Act: -0.0004

Data Index: 1254477 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4008. Min Act: -0.0004

Data Index: 1034668 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3988. Min Act: -0.0004

Data Index: 527303 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3977. Min Act: -0.0004

Data Index: 252962 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4106. Min Act: -0.0004

Data Index: 246612 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3961. Min Act: -0.0004

Data Index: 1333415 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3947. Min Act: -0.0004

Data Index: 716541 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3944. Min Act: -0.0004

Data Index: 414739 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3922. Min Act: -0.0004

Data Index: 33169 (C4 (Web Text))

Max Activating Token Index: 784