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

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

Neuron 4814 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.6372. Min Act: -0.0001

Data Index: 310269 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.6255. Min Act: -0.0001

Data Index: 1197982 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5451. Min Act: -0.0001

Data Index: 310227 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5900. Min Act: -0.0001

Data Index: 275560 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.6065. Min Act: -0.0001

Data Index: 863369 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5125. Min Act: -0.0001

Data Index: 702464 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5407. Min Act: -0.0001

Data Index: 674797 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5588. Min Act: -0.0001

Data Index: 757793 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4705. Min Act: -0.0001

Data Index: 972007 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4988. Min Act: -0.0001

Data Index: 1259083 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5129. Min Act: -0.0001

Data Index: 448385 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4948. Min Act: -0.0001

Data Index: 433274 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4979. Min Act: -0.0001

Data Index: 234333 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4681. Min Act: -0.0001

Data Index: 1255403 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4694. Min Act: -0.0001

Data Index: 905283 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4855. Min Act: -0.0001

Data Index: 683210 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4737. Min Act: -0.0001

Data Index: 834136 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4429. Min Act: -0.0001

Data Index: 1049402 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4656. Min Act: -0.0001

Data Index: 23641 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5096. Min Act: -0.0001

Data Index: 216052 (C4 (Web Text))

Max Activating Token Index: 614