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

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

Neuron 1591 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: 0.0090. Min Range: -0.0090

Max Act: 0.0088. Min Act: -0.0006

Data Index: 222155 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1151061 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0006

Data Index: 600340 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0006

Data Index: 923097 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0005

Data Index: 1341003 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0005

Data Index: 436338 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0005

Data Index: 442498 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0006

Data Index: 452156 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0005

Data Index: 684686 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0005

Data Index: 1600071 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0084. Min Act: -0.0006

Data Index: 207376 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0084. Min Act: -0.0005

Data Index: 1484571 (Python Code)

Max Activating Token Index: 935

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1568362 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1134595 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1149060 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0006

Data Index: 727254 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1586546 (Python Code)

Max Activating Token Index: 842

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0006

Data Index: 238022 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1108603 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1245641 (C4 (Web Text))

Max Activating Token Index: 109