Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 824 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.3057. Min Act: -0.0000

Data Index: 361548 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.2838. Min Act: -0.0000

Data Index: 309255 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1074731 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1312808 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.2119. Min Act: -0.0000

Data Index: 304410 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.2146. Min Act: -0.0000

Data Index: 904705 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1150094 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.1767. Min Act: -0.0000

Data Index: 1068879 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1206209 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.1546. Min Act: -0.0000

Data Index: 36739 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.0785. Min Act: -0.0000

Data Index: 229639 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.1372. Min Act: -0.0000

Data Index: 182661 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.0946. Min Act: -0.0000

Data Index: 54026 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.0907. Min Act: -0.0000

Data Index: 568401 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.0906. Min Act: -0.0000

Data Index: 959502 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.0645. Min Act: -0.0000

Data Index: 785240 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.0547. Min Act: -0.0000

Data Index: 253560 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.0488. Min Act: -0.0000

Data Index: 513421 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 1.3057. Min Range: -1.3057

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1119175 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 1.3057. Min Range: -1.3057

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1204004 (C4 (Web Text))

Max Activating Token Index: 818