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

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

Neuron 1821 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: 0.6652. Min Range: -0.6652

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1470215 (Python Code)

Max Activating Token Index: 674

Text #1

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1441647 (Python Code)

Max Activating Token Index: 948

Text #2

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1411549 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1536333 (Python Code)

Max Activating Token Index: 559

Text #4

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1630231 (Python Code)

Max Activating Token Index: 566

Text #5

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1542074 (Python Code)

Max Activating Token Index: 123

Text #6

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1558724 (Python Code)

Max Activating Token Index: 987

Text #7

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1368788 (Python Code)

Max Activating Token Index: 377

Text #8

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1494613 (Python Code)

Max Activating Token Index: 435

Text #9

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1479191 (Python Code)

Max Activating Token Index: 419

Text #10

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1548064 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1485225 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1479092 (Python Code)

Max Activating Token Index: 104

Text #13

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1363064 (Python Code)

Max Activating Token Index: 353

Text #14

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1377866 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1560416 (Python Code)

Max Activating Token Index: 688

Text #16

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1440084 (Python Code)

Max Activating Token Index: 991

Text #17

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1538381 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1505185 (Python Code)

Max Activating Token Index: 1011

Text #19

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1450928 (Python Code)

Max Activating Token Index: 625