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

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

Neuron 1209 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: 0.0110. Min Range: -0.0110

Max Act: 0.0110. Min Act: -0.0006

Data Index: 637020 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0103. Min Act: -0.0006

Data Index: 335138 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1091526 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0095. Min Act: -0.0006

Data Index: 860748 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0094. Min Act: -0.0006

Data Index: 533682 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0093. Min Act: -0.0006

Data Index: 259177 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0090. Min Act: -0.0006

Data Index: 208442 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0093. Min Act: -0.0006

Data Index: 84628 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0093. Min Act: -0.0006

Data Index: 388558 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0092. Min Act: -0.0007

Data Index: 104727 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0089. Min Act: -0.0006

Data Index: 614543 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0091. Min Act: -0.0006

Data Index: 413118 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1005706 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0090. Min Act: -0.0006

Data Index: 464741 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0090. Min Act: -0.0005

Data Index: 1569110 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0089. Min Act: -0.0006

Data Index: 97675 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0089. Min Act: -0.0006

Data Index: 45203 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0085. Min Act: -0.0006

Data Index: 766117 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1135449 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0087. Min Act: -0.0006

Data Index: 577138 (C4 (Web Text))

Max Activating Token Index: 999