Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3600 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.1306. Min Act: -0.0001

Data Index: 940284 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0429. Min Act: -0.0001

Data Index: 206022 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.1468. Min Act: -0.0001

Data Index: 765113 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0792. Min Act: -0.0001

Data Index: 955304 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.1175. Min Act: -0.0001

Data Index: 657582 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9496. Min Act: -0.0001

Data Index: 627948 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9376. Min Act: -0.0001

Data Index: 652028 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9536. Min Act: -0.0001

Data Index: 1324937 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9863. Min Act: -0.0001

Data Index: 1047037 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9446. Min Act: -0.0001

Data Index: 790626 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9639. Min Act: -0.0001

Data Index: 617923 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9387. Min Act: -0.0001

Data Index: 740886 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8987. Min Act: -0.0001

Data Index: 842883 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9334. Min Act: -0.0001

Data Index: 341262 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9335. Min Act: -0.0001

Data Index: 1135277 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8527. Min Act: -0.0001

Data Index: 1309104 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9744. Min Act: -0.0001

Data Index: 491180 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9220. Min Act: -0.0001

Data Index: 633080 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9721. Min Act: -0.0001

Data Index: 441088 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9543. Min Act: -0.0001

Data Index: 43450 (C4 (Web Text))

Max Activating Token Index: 265