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

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

Neuron 717 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: 0.7125. Min Range: -0.7125

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1484846 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1378220 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1447361 (Python Code)

Max Activating Token Index: 245

Text #3

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1578231 (Python Code)

Max Activating Token Index: 188

Text #4

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1417957 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1626203 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1571056 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1361981 (Python Code)

Max Activating Token Index: 180

Text #8

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1650569 (Python Code)

Max Activating Token Index: 545

Text #9

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5995. Min Act: -0.0000

Data Index: 999623 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1433237 (Python Code)

Max Activating Token Index: 329

Text #11

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1462009 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1539414 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1396130 (Python Code)

Max Activating Token Index: 447

Text #14

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1515486 (Python Code)

Max Activating Token Index: 520

Text #15

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1114039 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1565152 (Python Code)

Max Activating Token Index: 431

Text #17

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1578700 (Python Code)

Max Activating Token Index: 617

Text #18

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1379114 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1604543 (Python Code)

Max Activating Token Index: 65