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

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

Neuron 1305 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: -0.0006

Data Index: 555716 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0569. Min Act: -0.0005

Data Index: 1223672 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0545. Min Act: -0.0006

Data Index: 720135 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0542. Min Act: -0.0006

Data Index: 433832 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0534. Min Act: -0.0006

Data Index: 1181628 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0542. Min Act: -0.0005

Data Index: 53060 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0510. Min Act: -0.0006

Data Index: 314722 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0485. Min Act: -0.0006

Data Index: 862751 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0495. Min Act: -0.0006

Data Index: 360222 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0505. Min Act: -0.0005

Data Index: 57850 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0500. Min Act: -0.0006

Data Index: 347051 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0475. Min Act: -0.0006

Data Index: 1061870 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0481. Min Act: -0.0006

Data Index: 1182847 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0483. Min Act: -0.0005

Data Index: 979027 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0461. Min Act: -0.0005

Data Index: 1066609 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0468. Min Act: -0.0005

Data Index: 705499 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0466. Min Act: -0.0006

Data Index: 929956 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0445. Min Act: -0.0005

Data Index: 537973 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0454. Min Act: -0.0006

Data Index: 1077119 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0445. Min Act: -0.0006

Data Index: 498969 (C4 (Web Text))

Max Activating Token Index: 523