Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 626 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.7532. Min Range: -3.7532

Max Act: 3.7532. Min Act: -0.0001

Data Index: 1423730 (Python Code)

Max Activating Token Index: 986

Text #1

Max Range: 3.7532. Min Range: -3.7532

Max Act: 3.2779. Min Act: -0.0001

Data Index: 1513165 (Python Code)

Max Activating Token Index: 273

Text #2

Max Range: 3.7532. Min Range: -3.7532

Max Act: 3.1793. Min Act: -0.0001

Data Index: 1461866 (Python Code)

Max Activating Token Index: 41

Text #3

Max Range: 3.7532. Min Range: -3.7532

Max Act: 3.0815. Min Act: -0.0001

Data Index: 1379377 (Python Code)

Max Activating Token Index: 317

Text #4

Max Range: 3.7532. Min Range: -3.7532

Max Act: 3.0829. Min Act: -0.0001

Data Index: 1541264 (Python Code)

Max Activating Token Index: 927

Text #5

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.8016. Min Act: -0.0001

Data Index: 1494607 (Python Code)

Max Activating Token Index: 356

Text #6

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.8952. Min Act: -0.0001

Data Index: 1636309 (Python Code)

Max Activating Token Index: 160

Text #7

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.8856. Min Act: -0.0001

Data Index: 1586105 (Python Code)

Max Activating Token Index: 97

Text #8

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.9720. Min Act: -0.0001

Data Index: 1450020 (Python Code)

Max Activating Token Index: 249

Text #9

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.6947. Min Act: -0.0001

Data Index: 1504597 (Python Code)

Max Activating Token Index: 326

Text #10

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.5264. Min Act: -0.0001

Data Index: 1383770 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.8732. Min Act: -0.0001

Data Index: 1401196 (Python Code)

Max Activating Token Index: 460

Text #12

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.8511. Min Act: -0.0001

Data Index: 1645218 (Python Code)

Max Activating Token Index: 349

Text #13

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.5972. Min Act: -0.0001

Data Index: 1541721 (Python Code)

Max Activating Token Index: 917

Text #14

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.7164. Min Act: -0.0001

Data Index: 1409734 (Python Code)

Max Activating Token Index: 603

Text #15

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.4942. Min Act: -0.0001

Data Index: 1349978 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.5815. Min Act: -0.0001

Data Index: 1482248 (Python Code)

Max Activating Token Index: 24

Text #17

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.5708. Min Act: -0.0001

Data Index: 1435454 (Python Code)

Max Activating Token Index: 463

Text #18

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.4455. Min Act: -0.0001

Data Index: 1413165 (Python Code)

Max Activating Token Index: 945

Text #19

Max Range: 3.7532. Min Range: -3.7532

Max Act: 2.4137. Min Act: -0.0001

Data Index: 1455363 (Python Code)

Max Activating Token Index: 681