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

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

Neuron 979 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.7863. Min Act: -0.0000

Data Index: 649655 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.5037. Min Act: -0.0000

Data Index: 393964 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.5255. Min Act: -0.0000

Data Index: 556425 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.4534. Min Act: -0.0000

Data Index: 684345 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.4081. Min Act: -0.0000

Data Index: 471018 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.3616. Min Act: -0.0000

Data Index: 651542 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.3250. Min Act: -0.0000

Data Index: 1034265 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.3483. Min Act: -0.0000

Data Index: 968995 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.3151. Min Act: -0.0000

Data Index: 325532 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.1503. Min Act: -0.0000

Data Index: 935524 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.2180. Min Act: -0.0000

Data Index: 619662 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.2033. Min Act: -0.0000

Data Index: 913096 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.2017. Min Act: -0.0000

Data Index: 995996 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1352760 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.0953. Min Act: -0.0000

Data Index: 899497 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.1301. Min Act: -0.0000

Data Index: 109639 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.1521. Min Act: -0.0000

Data Index: 270129 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.2132. Min Act: -0.0000

Data Index: 99167 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.1190. Min Act: -0.0000

Data Index: 175075 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1354110 (C4 (Web Text))

Max Activating Token Index: 916