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

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

Neuron 5373 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0676. Min Range: -2.0676

Max Act: 2.0676. Min Act: -0.0000

Data Index: 1220630 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.6083. Min Act: -0.0000

Data Index: 247899 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.4563. Min Act: -0.0000

Data Index: 502691 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.4613. Min Act: -0.0000

Data Index: 303341 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.5479. Min Act: -0.0000

Data Index: 39078 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.3928. Min Act: -0.0000

Data Index: 149600 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.3081. Min Act: -0.0000

Data Index: 306550 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.2607. Min Act: -0.0000

Data Index: 700232 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.3051. Min Act: -0.0000

Data Index: 233281 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1152408 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.1947. Min Act: -0.0000

Data Index: 54676 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.0917. Min Act: -0.0000

Data Index: 813024 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.1314. Min Act: -0.0000

Data Index: 113820 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.2114. Min Act: -0.0000

Data Index: 756634 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.2639. Min Act: -0.0000

Data Index: 75269 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1280118 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.1425. Min Act: -0.0000

Data Index: 217739 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.1028. Min Act: -0.0000

Data Index: 699598 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.0847. Min Act: -0.0000

Data Index: 632900 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 2.0676. Min Range: -2.0676

Max Act: 1.0863. Min Act: -0.0000

Data Index: 540458 (C4 (Web Text))

Max Activating Token Index: 733