Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 12 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3934. Min Act: -0.0000

Data Index: 627755 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1247250 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1189319 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1427514 (Python Code)

Max Activating Token Index: 292

Text #4

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1501223 (Python Code)

Max Activating Token Index: 334

Text #5

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1036253 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2996. Min Act: -0.0000

Data Index: 187315 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1060937 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1124818 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2905. Min Act: -0.0000

Data Index: 991337 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3051. Min Act: -0.0000

Data Index: 120956 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1442968 (Python Code)

Max Activating Token Index: 132

Text #12

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1531354 (Python Code)

Max Activating Token Index: 836

Text #13

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2670. Min Act: -0.0000

Data Index: 747437 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1621276 (Python Code)

Max Activating Token Index: 748

Text #15

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1530834 (Python Code)

Max Activating Token Index: 417

Text #16

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1525495 (Python Code)

Max Activating Token Index: 44

Text #17

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2645. Min Act: -0.0000

Data Index: 751203 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2789. Min Act: -0.0000

Data Index: 367920 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2685. Min Act: -0.0000

Data Index: 732318 (C4 (Web Text))

Max Activating Token Index: 409