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

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

Neuron 598 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: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0006

Data Index: 757480 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1215740 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0068. Min Act: -0.0006

Data Index: 64345 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0006

Data Index: 294647 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0006

Data Index: 532822 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0006

Data Index: 756284 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1200000 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0066. Min Act: -0.0006

Data Index: 653939 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1152266 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0006

Data Index: 785346 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0006

Data Index: 991205 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0066. Min Act: -0.0006

Data Index: 722624 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0005

Data Index: 623246 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0005

Data Index: 903121 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0006

Data Index: 730006 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0006

Data Index: 864879 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1017080 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0005

Data Index: 1576979 (Python Code)

Max Activating Token Index: 596

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0006

Data Index: 115606 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0006

Data Index: 320966 (C4 (Web Text))

Max Activating Token Index: 372