Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5472 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6268. Min Range: -2.6268

Max Act: 2.6268. Min Act: 0.0000

Data Index: 142368 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 2.6268. Min Range: -2.6268

Max Act: 2.4473. Min Act: 0.0000

Data Index: 1242381 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 2.6268. Min Range: -2.6268

Max Act: 2.4133. Min Act: 0.0000

Data Index: 185806 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 2.6268. Min Range: -2.6268

Max Act: 2.3849. Min Act: 0.0000

Data Index: 1112989 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 2.6268. Min Range: -2.6268

Max Act: 2.1227. Min Act: 0.0000

Data Index: 60710 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.6713. Min Act: -0.0000

Data Index: 1403418 (Python Code)

Max Activating Token Index: 986

Text #6

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.7460. Min Act: -0.0000

Data Index: 1417553 (Python Code)

Max Activating Token Index: 198

Text #7

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.7819. Min Act: 0.0000

Data Index: 1265480 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.6429. Min Act: -0.0000

Data Index: 1367870 (Python Code)

Max Activating Token Index: 547

Text #9

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.7032. Min Act: 0.0000

Data Index: 616900 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.7043. Min Act: -0.0000

Data Index: 1231858 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.5946. Min Act: 0.0000

Data Index: 81472 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.7170. Min Act: -0.0000

Data Index: 1399602 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.4224. Min Act: -0.0000

Data Index: 1620853 (Python Code)

Max Activating Token Index: 866

Text #14

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1232462 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.4362. Min Act: -0.0000

Data Index: 1499270 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.4335. Min Act: 0.0000

Data Index: 222678 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.5744. Min Act: -0.0000

Data Index: 1361893 (Python Code)

Max Activating Token Index: 702

Text #18

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.4422. Min Act: -0.0000

Data Index: 1391343 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 2.6268. Min Range: -2.6268

Max Act: 1.3806. Min Act: 0.0000

Data Index: 1280571 (C4 (Web Text))

Max Activating Token Index: 590