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

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

Neuron 1118 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0727. Min Act: -0.0002

Data Index: 975269 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0544. Min Act: -0.0003

Data Index: 1224232 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1471826 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0528. Min Act: -0.0003

Data Index: 194255 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0512. Min Act: -0.0003

Data Index: 324375 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1165802 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0498. Min Act: -0.0003

Data Index: 334477 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0490. Min Act: -0.0002

Data Index: 108027 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1165672 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0490. Min Act: -0.0003

Data Index: 44761 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0496. Min Act: -0.0003

Data Index: 314136 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1388431 (Python Code)

Max Activating Token Index: 153

Text #12

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1390550 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0487. Min Act: -0.0003

Data Index: 558491 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1135531 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0473. Min Act: -0.0002

Data Index: 305056 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0484. Min Act: -0.0003

Data Index: 301252 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1552660 (Python Code)

Max Activating Token Index: 554

Text #18

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1059784 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0466. Min Act: -0.0003

Data Index: 283039 (C4 (Web Text))

Max Activating Token Index: 329