Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 931 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.6614. Min Act: -0.0003

Data Index: 526389 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5538. Min Act: -0.0002

Data Index: 1610227 (Python Code)

Max Activating Token Index: 277

Text #2

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5236. Min Act: -0.0003

Data Index: 1071040 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5356. Min Act: -0.0003

Data Index: 815645 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5155. Min Act: -0.0003

Data Index: 995944 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4993. Min Act: -0.0003

Data Index: 712409 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4760. Min Act: -0.0002

Data Index: 1377428 (Python Code)

Max Activating Token Index: 576

Text #7

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4746. Min Act: -0.0002

Data Index: 1525754 (Python Code)

Max Activating Token Index: 603

Text #8

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4703. Min Act: -0.0002

Data Index: 1548513 (Python Code)

Max Activating Token Index: 170

Text #9

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4692. Min Act: -0.0003

Data Index: 987100 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4657. Min Act: -0.0002

Data Index: 1371493 (Python Code)

Max Activating Token Index: 419

Text #11

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4665. Min Act: -0.0002

Data Index: 1584474 (Python Code)

Max Activating Token Index: 608

Text #12

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4585. Min Act: -0.0002

Data Index: 1560291 (Python Code)

Max Activating Token Index: 257

Text #13

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4525. Min Act: -0.0002

Data Index: 1584557 (Python Code)

Max Activating Token Index: 782

Text #14

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4421. Min Act: -0.0003

Data Index: 794716 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4415. Min Act: -0.0002

Data Index: 1387544 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4417. Min Act: -0.0002

Data Index: 1621470 (Python Code)

Max Activating Token Index: 897

Text #17

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4229. Min Act: -0.0002

Data Index: 1572027 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4290. Min Act: -0.0002

Data Index: 1500005 (Python Code)

Max Activating Token Index: 125

Text #19

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4271. Min Act: -0.0002

Data Index: 1647749 (Python Code)

Max Activating Token Index: 585