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

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

Neuron 2505 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: 3.3449. Min Range: -3.3449

Max Act: 3.3449. Min Act: -0.0000

Data Index: 1280313 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.7964. Min Act: -0.0000

Data Index: 933505 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.7347. Min Act: -0.0000

Data Index: 919356 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.8398. Min Act: -0.0000

Data Index: 108353 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.6978. Min Act: -0.0000

Data Index: 656668 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.9075. Min Act: -0.0000

Data Index: 428110 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.7510. Min Act: -0.0000

Data Index: 1057092 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.7361. Min Act: -0.0000

Data Index: 1097115 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.4197. Min Act: -0.0000

Data Index: 1579928 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.3071. Min Act: -0.0000

Data Index: 143837 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.3531. Min Act: -0.0000

Data Index: 1259773 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.3335. Min Act: -0.0000

Data Index: 88554 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.3200. Min Act: -0.0000

Data Index: 596202 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.1974. Min Act: -0.0000

Data Index: 513826 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.2350. Min Act: -0.0000

Data Index: 1262862 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.1291. Min Act: -0.0000

Data Index: 112927 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.1372. Min Act: -0.0000

Data Index: 1019389 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.2355. Min Act: -0.0000

Data Index: 1254617 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.1181. Min Act: -0.0000

Data Index: 560438 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.0997. Min Act: -0.0000

Data Index: 981343 (C4 (Web Text))

Max Activating Token Index: 487