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

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

Neuron 722 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: 0.0073. Min Range: -0.0073

Max Act: 0.0073. Min Act: -0.0006

Data Index: 356281 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1532245 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0072. Min Act: -0.0006

Data Index: 962426 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0071. Min Act: -0.0006

Data Index: 269080 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0006

Data Index: 366680 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0071. Min Act: -0.0006

Data Index: 955764 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1288951 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0069. Min Act: -0.0006

Data Index: 983075 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0006

Data Index: 188493 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0006

Data Index: 517993 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1152397 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0006

Data Index: 775514 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0006

Data Index: 658343 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0006

Data Index: 675351 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0006

Data Index: 641960 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1278970 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0006

Data Index: 623259 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0006

Data Index: 754146 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0006

Data Index: 789470 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0006

Data Index: 189746 (C4 (Web Text))

Max Activating Token Index: 72