Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1581 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5350. Min Act: -0.0001

Data Index: 793782 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5569. Min Act: -0.0001

Data Index: 1002349 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4680. Min Act: -0.0001

Data Index: 242809 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5323. Min Act: -0.0001

Data Index: 662467 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5632. Min Act: -0.0001

Data Index: 1159423 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3401. Min Act: -0.0001

Data Index: 1143084 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4968. Min Act: -0.0001

Data Index: 1115142 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4027. Min Act: -0.0001

Data Index: 20134 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5045. Min Act: -0.0001

Data Index: 667318 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4070. Min Act: -0.0001

Data Index: 1117623 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4247. Min Act: -0.0001

Data Index: 468596 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3741. Min Act: -0.0001

Data Index: 1033158 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4302. Min Act: -0.0001

Data Index: 932257 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4441. Min Act: -0.0001

Data Index: 454644 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4109. Min Act: -0.0001

Data Index: 789164 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4052. Min Act: -0.0001

Data Index: 1072042 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4365. Min Act: -0.0001

Data Index: 420707 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4437. Min Act: -0.0001

Data Index: 789165 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3696. Min Act: -0.0001

Data Index: 1031806 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4073. Min Act: -0.0001

Data Index: 882258 (C4 (Web Text))

Max Activating Token Index: 792