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

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

Neuron 1484 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.7021. Min Act: -0.0000

Data Index: 1557295 (Python Code)

Max Activating Token Index: 164

Text #1

Max Range: 7.0540. Min Range: -7.0540

Max Act: 7.0218. Min Act: -0.0001

Data Index: 1486627 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 7.0540. Min Range: -7.0540

Max Act: 7.0540. Min Act: -0.0000

Data Index: 1648532 (Python Code)

Max Activating Token Index: 325

Text #3

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.7581. Min Act: -0.0000

Data Index: 1421692 (Python Code)

Max Activating Token Index: 345

Text #4

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.5529. Min Act: -0.0001

Data Index: 1363486 (Python Code)

Max Activating Token Index: 684

Text #5

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.8920. Min Act: -0.0000

Data Index: 1408574 (Python Code)

Max Activating Token Index: 119

Text #6

Max Range: 7.0540. Min Range: -7.0540

Max Act: 7.0479. Min Act: -0.0000

Data Index: 1633013 (Python Code)

Max Activating Token Index: 101

Text #7

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.9900. Min Act: -0.0000

Data Index: 1561117 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.7073. Min Act: -0.0001

Data Index: 1641586 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.7241. Min Act: -0.0000

Data Index: 1470365 (Python Code)

Max Activating Token Index: 877

Text #10

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.4601. Min Act: -0.0000

Data Index: 1620028 (Python Code)

Max Activating Token Index: 245

Text #11

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.4702. Min Act: -0.0000

Data Index: 1391155 (Python Code)

Max Activating Token Index: 799

Text #12

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.1946. Min Act: -0.0000

Data Index: 1466203 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.5620. Min Act: -0.0001

Data Index: 1378713 (Python Code)

Max Activating Token Index: 644

Text #14

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.5334. Min Act: -0.0001

Data Index: 1452979 (Python Code)

Max Activating Token Index: 227

Text #15

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.7099. Min Act: -0.0000

Data Index: 1554325 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.6768. Min Act: -0.0001

Data Index: 1441537 (Python Code)

Max Activating Token Index: 142

Text #17

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.4874. Min Act: -0.0001

Data Index: 1625106 (Python Code)

Max Activating Token Index: 653

Text #18

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.1961. Min Act: -0.0000

Data Index: 1472043 (Python Code)

Max Activating Token Index: 891

Text #19

Max Range: 7.0540. Min Range: -7.0540

Max Act: 6.6386. Min Act: -0.0001

Data Index: 1411789 (Python Code)

Max Activating Token Index: 394