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

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

Neuron 611 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2079. Min Range: -5.2079

Max Act: 5.2079. Min Act: -0.0001

Data Index: 609377 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 5.2079. Min Range: -5.2079

Max Act: 5.1024. Min Act: -0.0000

Data Index: 755763 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.7285. Min Act: -0.0001

Data Index: 645941 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.8565. Min Act: -0.0001

Data Index: 928845 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.4991. Min Act: -0.0001

Data Index: 720565 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.4631. Min Act: -0.0001

Data Index: 483097 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.6332. Min Act: -0.0001

Data Index: 807323 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.3394. Min Act: -0.0001

Data Index: 241270 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.0601. Min Act: -0.0001

Data Index: 849692 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.3741. Min Act: -0.0001

Data Index: 284330 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.0793. Min Act: -0.0000

Data Index: 935000 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.1547. Min Act: -0.0000

Data Index: 654140 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.0414. Min Act: -0.0000

Data Index: 597815 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.1651. Min Act: -0.0001

Data Index: 151153 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.1775. Min Act: -0.0000

Data Index: 1222787 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 5.2079. Min Range: -5.2079

Max Act: 3.9522. Min Act: -0.0001

Data Index: 640505 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.1002. Min Act: -0.0001

Data Index: 814259 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 5.2079. Min Range: -5.2079

Max Act: 3.7498. Min Act: -0.0000

Data Index: 1259237 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.0603. Min Act: -0.0001

Data Index: 112287 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 5.2079. Min Range: -5.2079

Max Act: 4.0364. Min Act: -0.0001

Data Index: 1173047 (C4 (Web Text))

Max Activating Token Index: 469