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

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

Neuron 695 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5438. Min Range: -4.5438

Max Act: 4.5438. Min Act: -0.0000

Data Index: 1542636 (Python Code)

Max Activating Token Index: 230

Text #1

Max Range: 4.5438. Min Range: -4.5438

Max Act: 4.1695. Min Act: -0.0000

Data Index: 1504650 (Python Code)

Max Activating Token Index: 520

Text #2

Max Range: 4.5438. Min Range: -4.5438

Max Act: 3.3700. Min Act: -0.0000

Data Index: 1534927 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 4.5438. Min Range: -4.5438

Max Act: 3.3737. Min Act: -0.0000

Data Index: 1470883 (Python Code)

Max Activating Token Index: 463

Text #4

Max Range: 4.5438. Min Range: -4.5438

Max Act: 3.3588. Min Act: -0.0000

Data Index: 995619 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.7530. Min Act: -0.0000

Data Index: 1497319 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.6811. Min Act: -0.0000

Data Index: 1388831 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.7942. Min Act: -0.0000

Data Index: 880945 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.6487. Min Act: -0.0000

Data Index: 912498 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.8384. Min Act: -0.0000

Data Index: 1564614 (Python Code)

Max Activating Token Index: 573

Text #10

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.5308. Min Act: -0.0000

Data Index: 543624 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.3571. Min Act: -0.0000

Data Index: 131490 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.3339. Min Act: -0.0000

Data Index: 1549624 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.4887. Min Act: -0.0000

Data Index: 1560900 (Python Code)

Max Activating Token Index: 674

Text #14

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.2743. Min Act: -0.0000

Data Index: 1034233 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.2550. Min Act: -0.0000

Data Index: 777265 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.3715. Min Act: -0.0000

Data Index: 850630 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.3549. Min Act: -0.0000

Data Index: 248898 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.2250. Min Act: -0.0000

Data Index: 794830 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 4.5438. Min Range: -4.5438

Max Act: 2.3447. Min Act: -0.0000

Data Index: 1440402 (Python Code)

Max Activating Token Index: 385