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

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

Neuron 3703 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0296. Min Range: -1.0296

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1112490 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.0296. Min Range: -1.0296

Max Act: 1.0296. Min Act: -0.0000

Data Index: 1533844 (Python Code)

Max Activating Token Index: 57

Text #2

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1298243 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.9696. Min Act: -0.0000

Data Index: 1209332 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.9302. Min Act: -0.0000

Data Index: 1180864 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.8964. Min Act: -0.0000

Data Index: 1423666 (Python Code)

Max Activating Token Index: 908

Text #6

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1440475 (Python Code)

Max Activating Token Index: 802

Text #7

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1139236 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.8200. Min Act: -0.0000

Data Index: 58820 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.8146. Min Act: -0.0000

Data Index: 901985 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.8407. Min Act: -0.0000

Data Index: 41504 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.8127. Min Act: -0.0000

Data Index: 961742 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.8047. Min Act: -0.0000

Data Index: 435367 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.8489. Min Act: 0.0000

Data Index: 368033 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1319961 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.8090. Min Act: -0.0000

Data Index: 596356 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.7677. Min Act: -0.0000

Data Index: 888594 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1349913 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.7260. Min Act: -0.0000

Data Index: 567372 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 1.0296. Min Range: -1.0296

Max Act: 0.7967. Min Act: -0.0000

Data Index: 383281 (C4 (Web Text))

Max Activating Token Index: 947