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

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

Neuron 3930 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: 0.1718. Min Range: -0.1718

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1016022 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1626. Min Act: -0.0000

Data Index: 936334 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1322692 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1571. Min Act: -0.0000

Data Index: 94663 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1512. Min Act: -0.0001

Data Index: 438770 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1291405 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1577. Min Act: -0.0000

Data Index: 449467 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1425. Min Act: -0.0000

Data Index: 851048 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1377. Min Act: -0.0001

Data Index: 401915 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1038241 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1307. Min Act: -0.0000

Data Index: 376669 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1121728 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1286. Min Act: -0.0000

Data Index: 66545 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1347. Min Act: -0.0000

Data Index: 280613 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1256. Min Act: -0.0001

Data Index: 94342 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1276. Min Act: -0.0001

Data Index: 58678 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1312. Min Act: -0.0000

Data Index: 113720 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1254. Min Act: -0.0000

Data Index: 571856 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1179. Min Act: -0.0001

Data Index: 630236 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1209. Min Act: -0.0000

Data Index: 939724 (C4 (Web Text))

Max Activating Token Index: 441