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

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

Neuron 959 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5816. Min Act: -0.0001

Data Index: 1153143 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5881. Min Act: -0.0001

Data Index: 986562 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5520. Min Act: -0.0001

Data Index: 1144598 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1150164 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5410. Min Act: -0.0001

Data Index: 734366 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5277. Min Act: -0.0000

Data Index: 265012 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5017. Min Act: -0.0001

Data Index: 1234740 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5236. Min Act: -0.0000

Data Index: 98165 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4929. Min Act: -0.0001

Data Index: 1164730 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4800. Min Act: -0.0001

Data Index: 886754 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4714. Min Act: -0.0001

Data Index: 714083 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4953. Min Act: -0.0001

Data Index: 1196945 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4659. Min Act: -0.0001

Data Index: 234612 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1290853 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4712. Min Act: -0.0001

Data Index: 4172 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1171846 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4450. Min Act: -0.0000

Data Index: 386447 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4626. Min Act: -0.0001

Data Index: 1045519 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4460. Min Act: -0.0001

Data Index: 14465 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4259. Min Act: -0.0001

Data Index: 399986 (C4 (Web Text))

Max Activating Token Index: 914