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

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

Neuron 4086 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.6649. Min Act: -0.0000

Data Index: 307304 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.6317. Min Act: -0.0000

Data Index: 1364137 (Python Code)

Max Activating Token Index: 310

Text #2

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.5755. Min Act: -0.0000

Data Index: 740795 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.5090. Min Act: -0.0000

Data Index: 38463 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.2333. Min Act: -0.0000

Data Index: 202568 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1542174 (Python Code)

Max Activating Token Index: 736

Text #6

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1448440 (Python Code)

Max Activating Token Index: 707

Text #7

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1585244 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1559715 (Python Code)

Max Activating Token Index: 169

Text #9

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.2930. Min Act: -0.0000

Data Index: 1154301 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1400259 (Python Code)

Max Activating Token Index: 227

Text #11

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.1831. Min Act: -0.0000

Data Index: 1553818 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.1800. Min Act: -0.0000

Data Index: 1475350 (Python Code)

Max Activating Token Index: 378

Text #13

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.1359. Min Act: -0.0000

Data Index: 1547214 (Python Code)

Max Activating Token Index: 339

Text #14

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1583928 (Python Code)

Max Activating Token Index: 255

Text #15

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.1202. Min Act: -0.0000

Data Index: 1507295 (Python Code)

Max Activating Token Index: 418

Text #16

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1591233 (Python Code)

Max Activating Token Index: 958

Text #17

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.1078. Min Act: -0.0000

Data Index: 1596183 (Python Code)

Max Activating Token Index: 1016

Text #18

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.1001. Min Act: -0.0000

Data Index: 1466360 (Python Code)

Max Activating Token Index: 364

Text #19

Max Range: 1.6649. Min Range: -1.6649

Max Act: 0.9765. Min Act: -0.0000

Data Index: 1536237 (Python Code)

Max Activating Token Index: 644