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

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

Neuron 2027 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: 0.6175. Min Range: -0.6175

Max Act: 0.6175. Min Act: -0.0000

Data Index: 945302 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.5018. Min Act: -0.0000

Data Index: 732967 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1012924 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4682. Min Act: -0.0000

Data Index: 761116 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4675. Min Act: -0.0000

Data Index: 182905 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4699. Min Act: -0.0000

Data Index: 961317 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4574. Min Act: -0.0000

Data Index: 588341 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4489. Min Act: -0.0000

Data Index: 890028 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4465. Min Act: -0.0000

Data Index: 988246 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1318517 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1137122 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4430. Min Act: -0.0000

Data Index: 574307 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1281333 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4144. Min Act: -0.0000

Data Index: 52388 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1147295 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1220882 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4446. Min Act: -0.0000

Data Index: 242023 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4247. Min Act: -0.0000

Data Index: 776280 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4097. Min Act: -0.0000

Data Index: 826028 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1107265 (C4 (Web Text))

Max Activating Token Index: 712