Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1839 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.7020. Min Act: -0.0004

Data Index: 517356 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6770. Min Act: -0.0004

Data Index: 243255 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6365. Min Act: -0.0004

Data Index: 525075 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6155. Min Act: -0.0004

Data Index: 586426 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6138. Min Act: -0.0004

Data Index: 547057 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5945. Min Act: -0.0004

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6066. Min Act: -0.0004

Data Index: 547715 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6052. Min Act: -0.0004

Data Index: 1244051 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5824. Min Act: -0.0004

Data Index: 436436 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6002. Min Act: -0.0004

Data Index: 1297248 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6157. Min Act: -0.0004

Data Index: 921808 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5437. Min Act: -0.0004

Data Index: 521588 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5796. Min Act: -0.0004

Data Index: 283485 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6179. Min Act: -0.0004

Data Index: 1158666 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5753. Min Act: -0.0004

Data Index: 532989 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5940. Min Act: -0.0004

Data Index: 1087984 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5884. Min Act: -0.0004

Data Index: 248814 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5877. Min Act: -0.0004

Data Index: 701219 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5846. Min Act: -0.0004

Data Index: 133715 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5880. Min Act: -0.0004

Data Index: 939847 (C4 (Web Text))

Max Activating Token Index: 494