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

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

Neuron 1354 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1527290 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1269. Min Act: -0.0000

Data Index: 1433232 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1269. Min Act: -0.0000

Data Index: 1443727 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1444088 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1424317 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1445229 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1174. Min Act: -0.0000

Data Index: 1644769 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1612295 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1473222 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1574911 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1504443 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1424377 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1584191 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1497845 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1413641 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1644758 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1517151 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1631959 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1617811 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1431081 (Python Code)

Max Activating Token Index: 8