Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3115 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.7973. Min Act: -0.0001

Data Index: 376268 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.5967. Min Act: -0.0001

Data Index: 956735 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.6343. Min Act: -0.0001

Data Index: 1021288 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.5441. Min Act: -0.0001

Data Index: 320200 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.6290. Min Act: -0.0001

Data Index: 554345 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.5330. Min Act: -0.0001

Data Index: 1151971 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.4696. Min Act: -0.0001

Data Index: 339166 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.4646. Min Act: -0.0001

Data Index: 6830 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.4488. Min Act: -0.0001

Data Index: 480205 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.5272. Min Act: -0.0001

Data Index: 759035 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.3279. Min Act: -0.0001

Data Index: 576673 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.2938. Min Act: -0.0001

Data Index: 1217621 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.4068. Min Act: -0.0001

Data Index: 1023943 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.4307. Min Act: -0.0001

Data Index: 1001112 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.3607. Min Act: -0.0001

Data Index: 909261 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.3700. Min Act: -0.0001

Data Index: 1277096 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.2896. Min Act: -0.0001

Data Index: 193776 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.3210. Min Act: -0.0001

Data Index: 567886 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.3318. Min Act: -0.0001

Data Index: 407352 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 1.7973. Min Range: -1.7973

Max Act: 1.3442. Min Act: -0.0001

Data Index: 770935 (C4 (Web Text))

Max Activating Token Index: 992