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

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

Neuron 2025 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.6508. Min Act: -0.0000

Data Index: 8396 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.7529. Min Act: -0.0000

Data Index: 323652 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.6917. Min Act: -0.0000

Data Index: 1184606 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.3449. Min Act: -0.0000

Data Index: 574986 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.4607. Min Act: -0.0000

Data Index: 1322400 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.2344. Min Act: -0.0000

Data Index: 1241907 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.3870. Min Act: -0.0000

Data Index: 618759 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.3389. Min Act: -0.0000

Data Index: 603224 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.3137. Min Act: -0.0000

Data Index: 298362 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.1304. Min Act: -0.0000

Data Index: 319639 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.4333. Min Act: -0.0000

Data Index: 3635 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.2413. Min Act: -0.0000

Data Index: 1241024 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.4039. Min Act: -0.0000

Data Index: 1040549 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.3761. Min Act: -0.0000

Data Index: 369626 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.3399. Min Act: -0.0000

Data Index: 913506 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.2880. Min Act: -0.0000

Data Index: 817830 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.0932. Min Act: -0.0000

Data Index: 271965 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.0916. Min Act: -0.0000

Data Index: 684403 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.0662. Min Act: -0.0000

Data Index: 971971 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 4.7529. Min Range: -4.7529

Max Act: 4.2432. Min Act: -0.0000

Data Index: 1004813 (C4 (Web Text))

Max Activating Token Index: 181