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

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

Neuron 3712 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0840. Min Range: -1.0840

Max Act: 1.0840. Min Act: -0.0001

Data Index: 1381029 (Python Code)

Max Activating Token Index: 362

Text #1

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.8400. Min Act: -0.0001

Data Index: 1367381 (Python Code)

Max Activating Token Index: 851

Text #2

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.7421. Min Act: -0.0001

Data Index: 1466477 (Python Code)

Max Activating Token Index: 141

Text #3

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.7362. Min Act: -0.0001

Data Index: 1566851 (Python Code)

Max Activating Token Index: 925

Text #4

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.7344. Min Act: -0.0001

Data Index: 1509766 (Python Code)

Max Activating Token Index: 756

Text #5

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6971. Min Act: -0.0001

Data Index: 1646235 (Python Code)

Max Activating Token Index: 710

Text #6

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.7056. Min Act: -0.0001

Data Index: 1424929 (Python Code)

Max Activating Token Index: 351

Text #7

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6626. Min Act: -0.0001

Data Index: 1488638 (Python Code)

Max Activating Token Index: 565

Text #8

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1388412 (Python Code)

Max Activating Token Index: 112

Text #9

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6170. Min Act: -0.0001

Data Index: 1422290 (Python Code)

Max Activating Token Index: 138

Text #10

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6318. Min Act: -0.0001

Data Index: 569660 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6099. Min Act: -0.0001

Data Index: 1627491 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6020. Min Act: -0.0001

Data Index: 24321 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6196. Min Act: -0.0001

Data Index: 1427594 (Python Code)

Max Activating Token Index: 397

Text #14

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6217. Min Act: -0.0001

Data Index: 1617700 (Python Code)

Max Activating Token Index: 177

Text #15

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6267. Min Act: -0.0001

Data Index: 1388394 (Python Code)

Max Activating Token Index: 476

Text #16

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6212. Min Act: -0.0001

Data Index: 1410167 (Python Code)

Max Activating Token Index: 945

Text #17

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6231. Min Act: -0.0001

Data Index: 1219831 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.6036. Min Act: -0.0001

Data Index: 1359931 (Python Code)

Max Activating Token Index: 147

Text #19

Max Range: 1.0840. Min Range: -1.0840

Max Act: 0.5938. Min Act: -0.0001

Data Index: 471280 (C4 (Web Text))

Max Activating Token Index: 630