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

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

Neuron 4805 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1484. Min Range: -1.1484

Max Act: 1.1484. Min Act: -0.0000

Data Index: 691044 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6468. Min Act: -0.0000

Data Index: 920124 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6043. Min Act: -0.0000

Data Index: 356336 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6170. Min Act: -0.0000

Data Index: 286738 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.5652. Min Act: -0.0000

Data Index: 703212 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.5420. Min Act: -0.0000

Data Index: 830659 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1203384 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.5436. Min Act: -0.0000

Data Index: 327542 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.5376. Min Act: -0.0000

Data Index: 836248 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1337709 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.4913. Min Act: -0.0000

Data Index: 458284 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1096939 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.4647. Min Act: -0.0000

Data Index: 665013 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1147982 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.4782. Min Act: -0.0000

Data Index: 215123 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.4597. Min Act: -0.0000

Data Index: 996103 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.4542. Min Act: -0.0000

Data Index: 211262 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1309725 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.4302. Min Act: -0.0000

Data Index: 576160 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.4696. Min Act: -0.0000

Data Index: 775882 (C4 (Web Text))

Max Activating Token Index: 313