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

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

Neuron 2568 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5109. Min Range: -2.5109

Max Act: 2.5109. Min Act: -0.0000

Data Index: 887281 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 2.5109. Min Range: -2.5109

Max Act: 2.2259. Min Act: -0.0000

Data Index: 1113299 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.9795. Min Act: -0.0000

Data Index: 1228648 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 2.5109. Min Range: -2.5109

Max Act: 2.4509. Min Act: -0.0000

Data Index: 270014 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.8448. Min Act: -0.0000

Data Index: 787473 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.9569. Min Act: -0.0000

Data Index: 107502 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.9862. Min Act: -0.0000

Data Index: 521669 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.8626. Min Act: -0.0000

Data Index: 535181 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 2.5109. Min Range: -2.5109

Max Act: 2.0214. Min Act: -0.0000

Data Index: 428964 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.4272. Min Act: -0.0000

Data Index: 809056 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.4974. Min Act: -0.0000

Data Index: 1202214 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1331322 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.4837. Min Act: -0.0000

Data Index: 85421 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.2978. Min Act: -0.0000

Data Index: 757189 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.2146. Min Act: -0.0000

Data Index: 89177 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.2564. Min Act: -0.0000

Data Index: 65116 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.2216. Min Act: -0.0000

Data Index: 1299846 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.2083. Min Act: -0.0000

Data Index: 984688 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.1342. Min Act: -0.0000

Data Index: 768393 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 2.5109. Min Range: -2.5109

Max Act: 1.1147. Min Act: -0.0000

Data Index: 696920 (C4 (Web Text))

Max Activating Token Index: 308