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

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

Neuron 75 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.9958. Min Act: -0.0000

Data Index: 536360 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.8153. Min Act: -0.0000

Data Index: 938838 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.8885. Min Act: -0.0000

Data Index: 156961 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.8297. Min Act: -0.0000

Data Index: 1194331 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.9202. Min Act: -0.0000

Data Index: 204488 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.7322. Min Act: -0.0000

Data Index: 681197 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.7932. Min Act: -0.0000

Data Index: 548576 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.7964. Min Act: -0.0000

Data Index: 1295365 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.8718. Min Act: -0.0000

Data Index: 191537 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.8827. Min Act: -0.0000

Data Index: 1269167 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.8482. Min Act: -0.0000

Data Index: 236901 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.8375. Min Act: -0.0000

Data Index: 1055800 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.7209. Min Act: -0.0000

Data Index: 222070 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.5870. Min Act: -0.0000

Data Index: 1250006 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.8297. Min Act: -0.0000

Data Index: 91753 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.7602. Min Act: -0.0000

Data Index: 882000 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.6204. Min Act: -0.0000

Data Index: 365534 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.6144. Min Act: -0.0000

Data Index: 803964 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.7399. Min Act: -0.0000

Data Index: 841870 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.9958. Min Range: -1.9958

Max Act: 1.6451. Min Act: -0.0000

Data Index: 929069 (C4 (Web Text))

Max Activating Token Index: 81