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

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

Neuron 4128 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3223. Min Range: -2.3223

Max Act: 2.3223. Min Act: -0.0000

Data Index: 1484340 (Python Code)

Max Activating Token Index: 241

Text #1

Max Range: 2.3223. Min Range: -2.3223

Max Act: 2.1939. Min Act: -0.0000

Data Index: 1631628 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 2.3223. Min Range: -2.3223

Max Act: 2.0053. Min Act: -0.0000

Data Index: 1383602 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.8576. Min Act: -0.0000

Data Index: 1591572 (Python Code)

Max Activating Token Index: 210

Text #4

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.7911. Min Act: -0.0000

Data Index: 568958 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1410928 (Python Code)

Max Activating Token Index: 236

Text #6

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.7595. Min Act: -0.0000

Data Index: 822733 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.4673. Min Act: -0.0000

Data Index: 1532250 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1574927 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.3238. Min Act: -0.0000

Data Index: 1642992 (Python Code)

Max Activating Token Index: 544

Text #10

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1455233 (Python Code)

Max Activating Token Index: 101

Text #11

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.4582. Min Act: -0.0000

Data Index: 1487896 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.5317. Min Act: -0.0000

Data Index: 1589083 (Python Code)

Max Activating Token Index: 278

Text #13

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1562466 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.3544. Min Act: -0.0000

Data Index: 1363861 (Python Code)

Max Activating Token Index: 545

Text #15

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.3459. Min Act: -0.0000

Data Index: 1629114 (Python Code)

Max Activating Token Index: 165

Text #16

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.4315. Min Act: -0.0000

Data Index: 1572457 (Python Code)

Max Activating Token Index: 782

Text #17

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.4236. Min Act: -0.0000

Data Index: 1508835 (Python Code)

Max Activating Token Index: 168

Text #18

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1464205 (Python Code)

Max Activating Token Index: 389

Text #19

Max Range: 2.3223. Min Range: -2.3223

Max Act: 1.4714. Min Act: -0.0000

Data Index: 1598501 (Python Code)

Max Activating Token Index: 256