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

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

Neuron 673 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: 0.6936. Min Range: -0.6936

Max Act: 0.6936. Min Act: -0.0000

Data Index: 817500 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1280944 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5982. Min Act: -0.0000

Data Index: 31888 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5947. Min Act: -0.0000

Data Index: 45904 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6162. Min Act: -0.0000

Data Index: 17093 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5809. Min Act: -0.0000

Data Index: 223568 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1048574 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1455532 (Python Code)

Max Activating Token Index: 728

Text #8

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1369352 (Python Code)

Max Activating Token Index: 967

Text #9

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5681. Min Act: -0.0000

Data Index: 508006 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5513. Min Act: -0.0000

Data Index: 579633 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1617222 (Python Code)

Max Activating Token Index: 265

Text #12

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5388. Min Act: -0.0000

Data Index: 217724 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1201416 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5679. Min Act: -0.0000

Data Index: 51363 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1024068 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5406. Min Act: -0.0000

Data Index: 329808 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1353263 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1486267 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5460. Min Act: -0.0000

Data Index: 936104 (C4 (Web Text))

Max Activating Token Index: 89