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

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

Neuron 150 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2409. Min Range: -3.2409

Max Act: 3.2409. Min Act: -0.0001

Data Index: 74334 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.9239. Min Act: -0.0001

Data Index: 975953 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.6789. Min Act: -0.0001

Data Index: 1151534 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.5555. Min Act: -0.0000

Data Index: 479979 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.6987. Min Act: -0.0001

Data Index: 307925 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.5043. Min Act: -0.0001

Data Index: 554313 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.4644. Min Act: -0.0001

Data Index: 89355 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.1864. Min Act: -0.0001

Data Index: 310153 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.3996. Min Act: -0.0001

Data Index: 955838 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.3831. Min Act: -0.0001

Data Index: 716809 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.3839. Min Act: -0.0001

Data Index: 276149 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.2346. Min Act: -0.0001

Data Index: 430163 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.3539. Min Act: -0.0001

Data Index: 893097 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.3177. Min Act: -0.0001

Data Index: 45765 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.2481. Min Act: -0.0001

Data Index: 860258 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.0197. Min Act: -0.0001

Data Index: 689332 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.2418. Min Act: -0.0000

Data Index: 452076 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.2334. Min Act: -0.0001

Data Index: 1198012 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.0968. Min Act: -0.0001

Data Index: 533017 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 3.2409. Min Range: -3.2409

Max Act: 2.3168. Min Act: -0.0001

Data Index: 589592 (C4 (Web Text))

Max Activating Token Index: 334