Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 372 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.8391. Min Act: -0.0001

Data Index: 1008167 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.8514. Min Act: -0.0001

Data Index: 575561 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.7133. Min Act: -0.0001

Data Index: 251549 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.8467. Min Act: -0.0001

Data Index: 1493839 (Python Code)

Max Activating Token Index: 719

Text #4

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.7628. Min Act: -0.0001

Data Index: 1593963 (Python Code)

Max Activating Token Index: 730

Text #5

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.7716. Min Act: -0.0001

Data Index: 116140 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.6953. Min Act: -0.0001

Data Index: 1335470 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.6091. Min Act: -0.0001

Data Index: 1295125 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.6976. Min Act: -0.0001

Data Index: 898073 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.7156. Min Act: -0.0001

Data Index: 217773 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.6427. Min Act: -0.0001

Data Index: 1138607 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.7080. Min Act: -0.0001

Data Index: 784439 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.6840. Min Act: -0.0001

Data Index: 1205919 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.6865. Min Act: -0.0001

Data Index: 944388 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.6614. Min Act: -0.0001

Data Index: 800639 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.6827. Min Act: -0.0001

Data Index: 907764 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.7314. Min Act: -0.0001

Data Index: 82535 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.6789. Min Act: -0.0001

Data Index: 1446833 (Python Code)

Max Activating Token Index: 762

Text #18

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.6923. Min Act: -0.0001

Data Index: 601926 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.8514. Min Range: -0.8514

Max Act: 0.7120. Min Act: -0.0001

Data Index: 717403 (C4 (Web Text))

Max Activating Token Index: 487