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

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

Neuron 1265 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: 3.0787. Min Range: -3.0787

Max Act: 3.0787. Min Act: -0.0001

Data Index: 1335321 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.5670. Min Act: -0.0000

Data Index: 104723 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.5946. Min Act: -0.0000

Data Index: 17945 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.3912. Min Act: -0.0001

Data Index: 985659 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.3791. Min Act: -0.0001

Data Index: 726042 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.3530. Min Act: -0.0001

Data Index: 1143952 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.3340. Min Act: -0.0000

Data Index: 436153 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.1928. Min Act: -0.0001

Data Index: 533562 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.1710. Min Act: -0.0001

Data Index: 1167968 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.2710. Min Act: -0.0001

Data Index: 541282 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.0202. Min Act: -0.0001

Data Index: 627203 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.2266. Min Act: -0.0001

Data Index: 654694 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.0431. Min Act: -0.0001

Data Index: 66659 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.3386. Min Act: -0.0001

Data Index: 1129705 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.2061. Min Act: -0.0001

Data Index: 230955 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.1012. Min Act: -0.0001

Data Index: 1233177 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.1351. Min Act: -0.0000

Data Index: 1123466 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.0684. Min Act: -0.0000

Data Index: 92389 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.0414. Min Act: -0.0001

Data Index: 233095 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.0406. Min Act: -0.0001

Data Index: 405039 (C4 (Web Text))

Max Activating Token Index: 503