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

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

Neuron 1512 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: 0.6452. Min Range: -0.6452

Max Act: 0.6452. Min Act: -0.0000

Data Index: 736063 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5737. Min Act: -0.0000

Data Index: 797954 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4481. Min Act: -0.0000

Data Index: 585878 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1356026 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4221. Min Act: -0.0000

Data Index: 89238 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4219. Min Act: -0.0000

Data Index: 727931 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4235. Min Act: -0.0000

Data Index: 823424 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4341. Min Act: -0.0000

Data Index: 486996 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4001. Min Act: -0.0000

Data Index: 811864 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3945. Min Act: -0.0000

Data Index: 433123 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3832. Min Act: -0.0000

Data Index: 395317 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4164. Min Act: -0.0000

Data Index: 491931 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3488. Min Act: -0.0000

Data Index: 746529 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3811. Min Act: -0.0000

Data Index: 260451 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3708. Min Act: -0.0000

Data Index: 45743 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1076015 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3896. Min Act: -0.0000

Data Index: 218908 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3629. Min Act: -0.0000

Data Index: 521230 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3615. Min Act: -0.0000

Data Index: 274221 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3633. Min Act: -0.0000

Data Index: 857979 (C4 (Web Text))

Max Activating Token Index: 709