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

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

Neuron 835 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: 1.5398. Min Range: -1.5398

Max Act: 1.5398. Min Act: -0.0000

Data Index: 653194 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.2031. Min Act: -0.0000

Data Index: 1525918 (Python Code)

Max Activating Token Index: 786

Text #2

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.0947. Min Act: -0.0000

Data Index: 1605158 (Python Code)

Max Activating Token Index: 739

Text #3

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1526997 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1361549 (Python Code)

Max Activating Token Index: 559

Text #5

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1606165 (Python Code)

Max Activating Token Index: 763

Text #6

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.0398. Min Act: -0.0000

Data Index: 1560862 (Python Code)

Max Activating Token Index: 142

Text #7

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.0011. Min Act: -0.0000

Data Index: 1554514 (Python Code)

Max Activating Token Index: 76

Text #8

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1606988 (Python Code)

Max Activating Token Index: 380

Text #9

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1499747 (Python Code)

Max Activating Token Index: 324

Text #10

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1507715 (Python Code)

Max Activating Token Index: 911

Text #11

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1633111 (Python Code)

Max Activating Token Index: 349

Text #12

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1441022 (Python Code)

Max Activating Token Index: 272

Text #13

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1382721 (Python Code)

Max Activating Token Index: 319

Text #14

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1602703 (Python Code)

Max Activating Token Index: 480

Text #15

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1434489 (Python Code)

Max Activating Token Index: 157

Text #16

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1447534 (Python Code)

Max Activating Token Index: 221

Text #17

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1500033 (Python Code)

Max Activating Token Index: 1007

Text #18

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.9395. Min Act: -0.0000

Data Index: 1414488 (Python Code)

Max Activating Token Index: 537

Text #19

Max Range: 1.5398. Min Range: -1.5398

Max Act: 0.9572. Min Act: -0.0000

Data Index: 1462230 (Python Code)

Max Activating Token Index: 648