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

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

Neuron 1666 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.7261. Min Act: -0.0000

Data Index: 292994 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.5330. Min Act: -0.0000

Data Index: 861975 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.5201. Min Act: -0.0000

Data Index: 800081 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.4805. Min Act: -0.0000

Data Index: 944843 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.4606. Min Act: -0.0000

Data Index: 270402 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.4637. Min Act: -0.0000

Data Index: 824433 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.4411. Min Act: -0.0000

Data Index: 588283 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.3452. Min Act: -0.0000

Data Index: 745018 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.3398. Min Act: -0.0000

Data Index: 951986 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.3914. Min Act: -0.0000

Data Index: 146464 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.3876. Min Act: -0.0000

Data Index: 162354 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.4120. Min Act: -0.0000

Data Index: 721199 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.3812. Min Act: -0.0000

Data Index: 713622 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.3697. Min Act: -0.0000

Data Index: 794651 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.3648. Min Act: -0.0000

Data Index: 532989 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.4298. Min Act: -0.0000

Data Index: 799873 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.3380. Min Act: -0.0000

Data Index: 554958 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.3371. Min Act: -0.0000

Data Index: 653772 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.2785. Min Act: -0.0000

Data Index: 16129 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 1.7261. Min Range: -1.7261

Max Act: 1.2878. Min Act: -0.0000

Data Index: 885645 (C4 (Web Text))

Max Activating Token Index: 514