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

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

Neuron 4357 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: 1.8866. Min Range: -1.8866

Max Act: 1.8866. Min Act: -0.0000

Data Index: 1036329 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1100493 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.4212. Min Act: -0.0000

Data Index: 288506 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.5287. Min Act: -0.0000

Data Index: 8541 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.4931. Min Act: -0.0000

Data Index: 8975 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.5408. Min Act: -0.0000

Data Index: 1213811 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.3949. Min Act: -0.0000

Data Index: 914084 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.3929. Min Act: -0.0000

Data Index: 256742 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1273200 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.4674. Min Act: -0.0000

Data Index: 751015 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.4445. Min Act: -0.0000

Data Index: 1405969 (Python Code)

Max Activating Token Index: 825

Text #11

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.5003. Min Act: -0.0000

Data Index: 522086 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.4297. Min Act: -0.0000

Data Index: 1620557 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.3880. Min Act: -0.0000

Data Index: 629600 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.4335. Min Act: -0.0000

Data Index: 141144 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.3591. Min Act: -0.0000

Data Index: 1403170 (Python Code)

Max Activating Token Index: 1015

Text #16

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.3863. Min Act: -0.0000

Data Index: 822363 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.3446. Min Act: -0.0000

Data Index: 1593980 (Python Code)

Max Activating Token Index: 994

Text #18

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.3996. Min Act: -0.0000

Data Index: 316459 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.8866. Min Range: -1.8866

Max Act: 1.3608. Min Act: -0.0000

Data Index: 1273549 (C4 (Web Text))

Max Activating Token Index: 592