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

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

Neuron 2478 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.5787. Min Act: -0.0001

Data Index: 1463282 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.7792. Min Act: -0.0001

Data Index: 1541153 (Python Code)

Max Activating Token Index: 225

Text #2

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.5941. Min Act: -0.0001

Data Index: 1623461 (Python Code)

Max Activating Token Index: 1014

Text #3

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.7588. Min Act: -0.0001

Data Index: 1460887 (Python Code)

Max Activating Token Index: 756

Text #4

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.7476. Min Act: -0.0001

Data Index: 1513093 (Python Code)

Max Activating Token Index: 742

Text #5

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.5188. Min Act: -0.0001

Data Index: 1364086 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.3346. Min Act: -0.0001

Data Index: 1469035 (Python Code)

Max Activating Token Index: 535

Text #7

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.4545. Min Act: -0.0001

Data Index: 1642359 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 5.5787. Min Range: -5.5787

Max Act: 3.8923. Min Act: -0.0001

Data Index: 1506131 (Python Code)

Max Activating Token Index: 826

Text #9

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.1829. Min Act: -0.0001

Data Index: 1542014 (Python Code)

Max Activating Token Index: 94

Text #10

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.2241. Min Act: -0.0001

Data Index: 1573335 (Python Code)

Max Activating Token Index: 910

Text #11

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.3818. Min Act: -0.0001

Data Index: 1630625 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.0315. Min Act: -0.0001

Data Index: 1655632 (Python Code)

Max Activating Token Index: 324

Text #13

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.3180. Min Act: -0.0001

Data Index: 1394225 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 5.5787. Min Range: -5.5787

Max Act: 3.7922. Min Act: -0.0001

Data Index: 1566021 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.0784. Min Act: -0.0001

Data Index: 1498278 (Python Code)

Max Activating Token Index: 510

Text #16

Max Range: 5.5787. Min Range: -5.5787

Max Act: 3.8654. Min Act: -0.0001

Data Index: 1572542 (Python Code)

Max Activating Token Index: 116

Text #17

Max Range: 5.5787. Min Range: -5.5787

Max Act: 4.1583. Min Act: -0.0001

Data Index: 1451411 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 5.5787. Min Range: -5.5787

Max Act: 3.6256. Min Act: -0.0001

Data Index: 1587335 (Python Code)

Max Activating Token Index: 564

Text #19

Max Range: 5.5787. Min Range: -5.5787

Max Act: 3.9319. Min Act: -0.0001

Data Index: 1363598 (Python Code)

Max Activating Token Index: 51