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

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

Neuron 1342 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3162. Min Range: -6.3162

Max Act: 6.2018. Min Act: -0.0000

Data Index: 528565 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 6.3162. Min Range: -6.3162

Max Act: 6.3162. Min Act: -0.0000

Data Index: 904893 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 6.3162. Min Range: -6.3162

Max Act: 6.2773. Min Act: -0.0000

Data Index: 128005 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.7694. Min Act: -0.0000

Data Index: 143017 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.6189. Min Act: -0.0000

Data Index: 551564 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.9661. Min Act: -0.0000

Data Index: 913508 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.5610. Min Act: -0.0000

Data Index: 336237 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.5091. Min Act: -0.0000

Data Index: 1230205 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.2847. Min Act: -0.0000

Data Index: 1008815 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.3375. Min Act: -0.0000

Data Index: 216483 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.2345. Min Act: -0.0000

Data Index: 70952 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.5046. Min Act: -0.0000

Data Index: 524474 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 6.3162. Min Range: -6.3162

Max Act: 4.9900. Min Act: -0.0000

Data Index: 602425 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.1492. Min Act: -0.0000

Data Index: 8508 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.1006. Min Act: -0.0000

Data Index: 848938 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 6.3162. Min Range: -6.3162

Max Act: 4.8353. Min Act: -0.0000

Data Index: 1334690 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.1636. Min Act: -0.0000

Data Index: 813514 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.2463. Min Act: -0.0001

Data Index: 940396 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 6.3162. Min Range: -6.3162

Max Act: 5.0838. Min Act: -0.0000

Data Index: 147336 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 6.3162. Min Range: -6.3162

Max Act: 4.7246. Min Act: -0.0000

Data Index: 903438 (C4 (Web Text))

Max Activating Token Index: 683