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

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

Neuron 2685 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: 1.7546. Min Range: -1.7546

Max Act: 1.7546. Min Act: -0.0000

Data Index: 577008 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.5770. Min Act: -0.0000

Data Index: 1069602 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.6663. Min Act: -0.0000

Data Index: 909722 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.7451. Min Act: -0.0000

Data Index: 195493 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.7487. Min Act: -0.0000

Data Index: 989561 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.6307. Min Act: -0.0000

Data Index: 735103 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.6108. Min Act: -0.0000

Data Index: 670703 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.5964. Min Act: -0.0000

Data Index: 469693 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.5358. Min Act: -0.0000

Data Index: 216493 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.4313. Min Act: -0.0000

Data Index: 375709 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.5046. Min Act: -0.0000

Data Index: 541845 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.4890. Min Act: -0.0000

Data Index: 473985 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.4031. Min Act: -0.0000

Data Index: 873115 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.4177. Min Act: -0.0000

Data Index: 500902 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.4850. Min Act: -0.0000

Data Index: 422891 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.3918. Min Act: -0.0000

Data Index: 213826 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.5644. Min Act: -0.0000

Data Index: 502214 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1146643 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.4696. Min Act: -0.0000

Data Index: 490791 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.7546. Min Range: -1.7546

Max Act: 1.4468. Min Act: -0.0000

Data Index: 843067 (C4 (Web Text))

Max Activating Token Index: 459