Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 521 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0218. Min Range: -1.0218

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1090160 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 1.0218. Min Range: -1.0218

Max Act: 1.0218. Min Act: -0.0001

Data Index: 266224 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8084. Min Act: -0.0000

Data Index: 628026 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 1.0218. Min Range: -1.0218

Max Act: 1.0132. Min Act: -0.0000

Data Index: 900348 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.9335. Min Act: -0.0001

Data Index: 1111861 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8676. Min Act: -0.0001

Data Index: 602909 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.9265. Min Act: -0.0000

Data Index: 826950 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8812. Min Act: -0.0001

Data Index: 32672 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1164672 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8835. Min Act: -0.0000

Data Index: 373424 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8844. Min Act: -0.0001

Data Index: 176876 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8724. Min Act: -0.0001

Data Index: 240699 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8616. Min Act: -0.0001

Data Index: 373855 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8424. Min Act: -0.0001

Data Index: 1153378 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8816. Min Act: -0.0001

Data Index: 556621 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8156. Min Act: -0.0001

Data Index: 339023 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8656. Min Act: -0.0000

Data Index: 930405 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8676. Min Act: -0.0000

Data Index: 334667 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.7830. Min Act: -0.0001

Data Index: 642747 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8781. Min Act: -0.0000

Data Index: 472260 (C4 (Web Text))

Max Activating Token Index: 834