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

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

Neuron 646 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1051922 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.0204. Min Range: -1.0204

Max Act: 1.0204. Min Act: -0.0000

Data Index: 565240 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.9025. Min Act: -0.0001

Data Index: 1194884 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.9218. Min Act: -0.0000

Data Index: 706245 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8230. Min Act: -0.0001

Data Index: 999249 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1216904 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8508. Min Act: -0.0001

Data Index: 742319 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8582. Min Act: -0.0001

Data Index: 570994 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.9150. Min Act: -0.0001

Data Index: 176195 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8303. Min Act: -0.0000

Data Index: 176460 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8261. Min Act: -0.0001

Data Index: 816666 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8232. Min Act: -0.0001

Data Index: 826950 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8387. Min Act: -0.0001

Data Index: 1146743 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8577. Min Act: -0.0001

Data Index: 961729 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8286. Min Act: -0.0001

Data Index: 959415 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8329. Min Act: -0.0001

Data Index: 1303964 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.7783. Min Act: -0.0001

Data Index: 381624 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1082992 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1098892 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8126. Min Act: -0.0000

Data Index: 61049 (C4 (Web Text))

Max Activating Token Index: 444