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

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

Neuron 988 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2645. Min Act: -0.0001

Data Index: 389870 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2616. Min Act: -0.0001

Data Index: 1300344 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2300. Min Act: -0.0001

Data Index: 1180649 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2341. Min Act: -0.0001

Data Index: 855387 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2298. Min Act: -0.0001

Data Index: 863486 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2263. Min Act: -0.0001

Data Index: 968401 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2162. Min Act: -0.0001

Data Index: 1080572 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2064. Min Act: -0.0001

Data Index: 181080 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2180. Min Act: -0.0001

Data Index: 53527 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2082. Min Act: -0.0001

Data Index: 168805 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2117. Min Act: -0.0001

Data Index: 367822 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2035. Min Act: -0.0001

Data Index: 322370 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2005. Min Act: -0.0001

Data Index: 474654 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1266970 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1969. Min Act: -0.0001

Data Index: 300534 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1980. Min Act: -0.0001

Data Index: 960926 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2040. Min Act: -0.0001

Data Index: 62360 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1957. Min Act: -0.0001

Data Index: 1252367 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1881. Min Act: -0.0001

Data Index: 16696 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1944. Min Act: -0.0001

Data Index: 615549 (C4 (Web Text))

Max Activating Token Index: 843