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

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

Neuron 397 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.9320. Min Act: -0.0001

Data Index: 1009960 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.7592. Min Act: -0.0001

Data Index: 741093 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.7338. Min Act: -0.0002

Data Index: 492790 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.6347. Min Act: -0.0001

Data Index: 391049 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.7021. Min Act: -0.0002

Data Index: 642043 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.7372. Min Act: -0.0001

Data Index: 974519 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.7074. Min Act: -0.0001

Data Index: 925368 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.7225. Min Act: -0.0001

Data Index: 337188 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.6116. Min Act: -0.0001

Data Index: 672742 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.6761. Min Act: -0.0001

Data Index: 245074 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.6375. Min Act: -0.0001

Data Index: 1101109 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.6109. Min Act: -0.0001

Data Index: 960125 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.6344. Min Act: -0.0001

Data Index: 700186 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.7047. Min Act: -0.0001

Data Index: 1358675 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.6274. Min Act: -0.0001

Data Index: 235809 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.6305. Min Act: -0.0002

Data Index: 87841 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.5732. Min Act: -0.0001

Data Index: 677343 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.5264. Min Act: -0.0001

Data Index: 1099696 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.5906. Min Act: -0.0001

Data Index: 996349 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.9320. Min Range: -0.9320

Max Act: 0.4970. Min Act: -0.0001

Data Index: 514399 (C4 (Web Text))

Max Activating Token Index: 696