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

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

Neuron 1820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1315770 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.8608. Min Act: -0.0000

Data Index: 272474 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.8493. Min Act: -0.0000

Data Index: 847986 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1196424 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.8211. Min Act: -0.0000

Data Index: 707723 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1180673 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1332790 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1230634 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7934. Min Act: -0.0000

Data Index: 97618 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7605. Min Act: -0.0000

Data Index: 424552 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7593. Min Act: -0.0000

Data Index: 128482 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1292523 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1126276 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7730. Min Act: -0.0000

Data Index: 887431 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7652. Min Act: -0.0000

Data Index: 65180 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7385. Min Act: -0.0000

Data Index: 396024 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.6482. Min Act: -0.0000

Data Index: 899255 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.6934. Min Act: -0.0000

Data Index: 226584 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7165. Min Act: -0.0000

Data Index: 948085 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.6884. Min Act: -0.0000

Data Index: 265140 (C4 (Web Text))

Max Activating Token Index: 358