Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 584 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.1774. Min Act: -0.0001

Data Index: 11600 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1048080 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9202. Min Act: -0.0001

Data Index: 116781 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8624. Min Act: -0.0001

Data Index: 1036261 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8821. Min Act: -0.0001

Data Index: 1187804 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8812. Min Act: -0.0001

Data Index: 177898 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8556. Min Act: -0.0001

Data Index: 573439 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8740. Min Act: -0.0001

Data Index: 657768 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8667. Min Act: -0.0001

Data Index: 978476 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8877. Min Act: -0.0001

Data Index: 510094 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8196. Min Act: -0.0001

Data Index: 1189171 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8134. Min Act: -0.0001

Data Index: 573411 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8395. Min Act: -0.0001

Data Index: 905703 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.7784. Min Act: -0.0001

Data Index: 16359 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8491. Min Act: -0.0001

Data Index: 436757 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.7782. Min Act: -0.0001

Data Index: 1342655 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.7930. Min Act: -0.0001

Data Index: 372995 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8017. Min Act: -0.0001

Data Index: 983515 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.7707. Min Act: -0.0001

Data Index: 1129761 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.7322. Min Act: -0.0001

Data Index: 584648 (C4 (Web Text))

Max Activating Token Index: 833