Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3623 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2265. Min Range: -1.2265

Max Act: 1.2265. Min Act: -0.0001

Data Index: 526370 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 1.2265. Min Range: -1.2265

Max Act: 1.0833. Min Act: -0.0001

Data Index: 597609 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 1.2265. Min Range: -1.2265

Max Act: 1.0253. Min Act: -0.0001

Data Index: 708382 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 1.2265. Min Range: -1.2265

Max Act: 1.1034. Min Act: -0.0001

Data Index: 1033781 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.9717. Min Act: -0.0001

Data Index: 1196396 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.9873. Min Act: -0.0001

Data Index: 175122 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.9846. Min Act: -0.0001

Data Index: 1146386 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 1.2265. Min Range: -1.2265

Max Act: 1.0377. Min Act: -0.0001

Data Index: 257315 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.8747. Min Act: -0.0001

Data Index: 992885 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.9916. Min Act: -0.0001

Data Index: 700768 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 1.2265. Min Range: -1.2265

Max Act: 1.0127. Min Act: -0.0001

Data Index: 880983 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.9549. Min Act: -0.0001

Data Index: 698901 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.9905. Min Act: -0.0001

Data Index: 635427 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.9980. Min Act: -0.0001

Data Index: 366411 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.9218. Min Act: -0.0001

Data Index: 381551 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.8831. Min Act: -0.0001

Data Index: 1339095 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.9156. Min Act: -0.0001

Data Index: 280381 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.9480. Min Act: -0.0001

Data Index: 342564 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.8843. Min Act: -0.0001

Data Index: 264904 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 1.2265. Min Range: -1.2265

Max Act: 0.8841. Min Act: -0.0001

Data Index: 900438 (C4 (Web Text))

Max Activating Token Index: 616