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

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

Neuron 4759 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4505. Min Range: -2.4505

Max Act: 2.3054. Min Act: -0.0000

Data Index: 180741 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 2.4505. Min Range: -2.4505

Max Act: 2.4505. Min Act: -0.0000

Data Index: 54459 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 2.4505. Min Range: -2.4505

Max Act: 2.1890. Min Act: -0.0000

Data Index: 602143 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 2.4505. Min Range: -2.4505

Max Act: 2.0570. Min Act: -0.0000

Data Index: 1270001 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 2.4505. Min Range: -2.4505

Max Act: 2.1294. Min Act: -0.0000

Data Index: 691424 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 2.4505. Min Range: -2.4505

Max Act: 2.1957. Min Act: -0.0000

Data Index: 1180553 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.9988. Min Act: -0.0000

Data Index: 1089300 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.9353. Min Act: -0.0000

Data Index: 972745 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.9632. Min Act: -0.0000

Data Index: 431483 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.8683. Min Act: -0.0000

Data Index: 712489 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.7816. Min Act: -0.0000

Data Index: 1017106 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 2.4505. Min Range: -2.4505

Max Act: 2.1303. Min Act: -0.0000

Data Index: 208412 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.9249. Min Act: -0.0000

Data Index: 1286711 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.9520. Min Act: -0.0000

Data Index: 1257733 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.7915. Min Act: -0.0000

Data Index: 97700 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.8492. Min Act: -0.0000

Data Index: 78181 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.8018. Min Act: -0.0000

Data Index: 1157659 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.8153. Min Act: -0.0000

Data Index: 226439 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.8122. Min Act: -0.0000

Data Index: 1310145 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 2.4505. Min Range: -2.4505

Max Act: 1.8567. Min Act: -0.0000

Data Index: 385449 (C4 (Web Text))

Max Activating Token Index: 605