Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 657 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0006

Data Index: 99888 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0005

Data Index: 449246 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0006

Data Index: 615778 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: -0.0006

Data Index: 709968 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1313969 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: -0.0006

Data Index: 15475 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: -0.0006

Data Index: 461796 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0086. Min Act: -0.0006

Data Index: 315469 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0086. Min Act: -0.0006

Data Index: 846200 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0086. Min Act: -0.0006

Data Index: 349583 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1098688 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0006

Data Index: 777975 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: -0.0006

Data Index: 294763 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1230562 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0006

Data Index: 167271 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0006

Data Index: 801249 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0006

Data Index: 884737 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0006

Data Index: 770940 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1641990 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0084. Min Act: -0.0006

Data Index: 239201 (C4 (Web Text))

Max Activating Token Index: 506