Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1997 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6512. Min Range: -3.6512

Max Act: 3.6512. Min Act: -0.0001

Data Index: 997623 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 3.6512. Min Range: -3.6512

Max Act: 3.5875. Min Act: -0.0001

Data Index: 97361 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 3.6512. Min Range: -3.6512

Max Act: 3.2954. Min Act: -0.0001

Data Index: 1245704 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 3.6512. Min Range: -3.6512

Max Act: 3.1312. Min Act: -0.0001

Data Index: 170216 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 3.6512. Min Range: -3.6512

Max Act: 3.0531. Min Act: -0.0001

Data Index: 1348728 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 3.6512. Min Range: -3.6512

Max Act: 3.1815. Min Act: -0.0001

Data Index: 211593 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 3.6512. Min Range: -3.6512

Max Act: 3.2424. Min Act: -0.0001

Data Index: 407470 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 3.6512. Min Range: -3.6512

Max Act: 3.0102. Min Act: -0.0001

Data Index: 574995 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 3.6512. Min Range: -3.6512

Max Act: 3.1739. Min Act: -0.0000

Data Index: 1071070 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 3.6512. Min Range: -3.6512

Max Act: 3.1601. Min Act: -0.0001

Data Index: 878098 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 3.6512. Min Range: -3.6512

Max Act: 2.5816. Min Act: -0.0000

Data Index: 237162 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 3.6512. Min Range: -3.6512

Max Act: 2.8449. Min Act: -0.0001

Data Index: 479516 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 3.6512. Min Range: -3.6512

Max Act: 2.6428. Min Act: -0.0001

Data Index: 799214 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 3.6512. Min Range: -3.6512

Max Act: 2.7240. Min Act: -0.0001

Data Index: 293661 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 3.6512. Min Range: -3.6512

Max Act: 2.7955. Min Act: -0.0000

Data Index: 416381 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 3.6512. Min Range: -3.6512

Max Act: 2.7970. Min Act: -0.0001

Data Index: 1217019 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 3.6512. Min Range: -3.6512

Max Act: 2.6587. Min Act: -0.0001

Data Index: 268422 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 3.6512. Min Range: -3.6512

Max Act: 2.6517. Min Act: -0.0001

Data Index: 912435 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 3.6512. Min Range: -3.6512

Max Act: 2.6247. Min Act: -0.0001

Data Index: 1340325 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 3.6512. Min Range: -3.6512

Max Act: 2.7502. Min Act: -0.0000

Data Index: 504131 (C4 (Web Text))

Max Activating Token Index: 291