Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1976 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0110. Min Act: -0.0006

Data Index: 704325 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0107. Min Act: -0.0006

Data Index: 701499 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0106. Min Act: -0.0006

Data Index: 66640 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0108. Min Act: -0.0006

Data Index: 922377 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1271326 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0108. Min Act: -0.0006

Data Index: 946559 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0105. Min Act: -0.0005

Data Index: 1257974 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0102. Min Act: -0.0006

Data Index: 95990 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1343302 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0104. Min Act: -0.0006

Data Index: 850204 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0104. Min Act: -0.0006

Data Index: 824042 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1294864 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1164601 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0103. Min Act: -0.0005

Data Index: 962940 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0103. Min Act: -0.0006

Data Index: 139069 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0101. Min Act: -0.0006

Data Index: 637676 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0103. Min Act: -0.0005

Data Index: 664304 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0103. Min Act: -0.0006

Data Index: 106856 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0103. Min Act: -0.0006

Data Index: 340406 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0102. Min Act: -0.0006

Data Index: 691629 (C4 (Web Text))

Max Activating Token Index: 631