Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1886 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.3023. Min Act: -0.0001

Data Index: 1040177 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2892. Min Act: -0.0001

Data Index: 387452 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2670. Min Act: -0.0001

Data Index: 500774 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2704. Min Act: -0.0001

Data Index: 599293 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2786. Min Act: -0.0001

Data Index: 1139195 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2496. Min Act: -0.0001

Data Index: 623400 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1140788 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2483. Min Act: -0.0001

Data Index: 355420 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2453. Min Act: -0.0001

Data Index: 1161096 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2373. Min Act: -0.0001

Data Index: 426335 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2293. Min Act: -0.0001

Data Index: 256100 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2458. Min Act: -0.0001

Data Index: 833852 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2230. Min Act: -0.0001

Data Index: 490321 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2284. Min Act: -0.0001

Data Index: 1065971 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1019307 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2246. Min Act: -0.0001

Data Index: 550673 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2147. Min Act: -0.0001

Data Index: 539579 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2272. Min Act: -0.0001

Data Index: 608082 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2118. Min Act: -0.0001

Data Index: 231700 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2158. Min Act: -0.0001

Data Index: 302071 (C4 (Web Text))

Max Activating Token Index: 618