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

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

Neuron 4887 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5846. Min Range: -3.5846

Max Act: 3.5846. Min Act: -0.0000

Data Index: 1632290 (Python Code)

Max Activating Token Index: 611

Text #1

Max Range: 3.5846. Min Range: -3.5846

Max Act: 3.5502. Min Act: -0.0000

Data Index: 937465 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 3.5846. Min Range: -3.5846

Max Act: 3.3426. Min Act: -0.0000

Data Index: 815840 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 3.5846. Min Range: -3.5846

Max Act: 3.1749. Min Act: -0.0000

Data Index: 456077 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 3.5846. Min Range: -3.5846

Max Act: 3.1989. Min Act: -0.0000

Data Index: 302312 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.9066. Min Act: -0.0000

Data Index: 267287 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.9769. Min Act: -0.0000

Data Index: 1050475 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.7606. Min Act: -0.0000

Data Index: 717740 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.8965. Min Act: -0.0000

Data Index: 352154 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.8635. Min Act: -0.0000

Data Index: 1029310 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.7447. Min Act: -0.0000

Data Index: 1325218 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.5463. Min Act: -0.0000

Data Index: 348367 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.5251. Min Act: -0.0000

Data Index: 537111 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.5278. Min Act: -0.0000

Data Index: 705530 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.6452. Min Act: -0.0000

Data Index: 275387 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.5535. Min Act: -0.0000

Data Index: 1282292 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.7344. Min Act: -0.0000

Data Index: 1565632 (Python Code)

Max Activating Token Index: 546

Text #17

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.7372. Min Act: -0.0000

Data Index: 156959 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.7044. Min Act: -0.0000

Data Index: 1296947 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 3.5846. Min Range: -3.5846

Max Act: 2.4047. Min Act: 0.0000

Data Index: 342815 (C4 (Web Text))

Max Activating Token Index: 369