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

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

Neuron 2503 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5362. Min Act: -0.0001

Data Index: 1611963 (Python Code)

Max Activating Token Index: 604

Text #1

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5266. Min Act: -0.0001

Data Index: 1424118 (Python Code)

Max Activating Token Index: 108

Text #2

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4921. Min Act: -0.0001

Data Index: 1429195 (Python Code)

Max Activating Token Index: 747

Text #3

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4812. Min Act: -0.0001

Data Index: 1527069 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4962. Min Act: -0.0001

Data Index: 656089 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4818. Min Act: -0.0001

Data Index: 1502317 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4856. Min Act: -0.0001

Data Index: 1596819 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4947. Min Act: -0.0001

Data Index: 1439351 (Python Code)

Max Activating Token Index: 290

Text #8

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4765. Min Act: -0.0001

Data Index: 676522 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4736. Min Act: -0.0001

Data Index: 603728 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4498. Min Act: -0.0001

Data Index: 352830 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4605. Min Act: -0.0001

Data Index: 1596970 (Python Code)

Max Activating Token Index: 586

Text #12

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4614. Min Act: -0.0001

Data Index: 1513080 (Python Code)

Max Activating Token Index: 400

Text #13

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4438. Min Act: -0.0001

Data Index: 1435352 (Python Code)

Max Activating Token Index: 934

Text #14

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4405. Min Act: -0.0001

Data Index: 418840 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4818. Min Act: -0.0001

Data Index: 669811 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4514. Min Act: -0.0001

Data Index: 1646953 (Python Code)

Max Activating Token Index: 868

Text #17

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4479. Min Act: -0.0001

Data Index: 73791 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4363. Min Act: -0.0001

Data Index: 570415 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4611. Min Act: -0.0001

Data Index: 1402113 (Python Code)

Max Activating Token Index: 866