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

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

Neuron 1596 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5994. Min Range: -2.5994

Max Act: 2.5994. Min Act: -0.0000

Data Index: 177839 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 2.5994. Min Range: -2.5994

Max Act: 2.3105. Min Act: -0.0000

Data Index: 1206613 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.8843. Min Act: -0.0000

Data Index: 1245973 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.9514. Min Act: -0.0000

Data Index: 397998 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.7383. Min Act: -0.0000

Data Index: 584249 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.6467. Min Act: -0.0000

Data Index: 554176 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.6997. Min Act: -0.0000

Data Index: 91087 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.6913. Min Act: -0.0001

Data Index: 1305465 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.6901. Min Act: -0.0000

Data Index: 624989 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.8340. Min Act: -0.0000

Data Index: 274422 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.6518. Min Act: -0.0000

Data Index: 243500 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.4733. Min Act: -0.0000

Data Index: 344712 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.6161. Min Act: -0.0000

Data Index: 1608261 (Python Code)

Max Activating Token Index: 663

Text #13

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.7149. Min Act: -0.0000

Data Index: 480413 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.6168. Min Act: -0.0000

Data Index: 1391658 (Python Code)

Max Activating Token Index: 429

Text #15

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.5133. Min Act: -0.0000

Data Index: 1338199 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.6913. Min Act: -0.0000

Data Index: 9765 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.5989. Min Act: -0.0000

Data Index: 1410056 (Python Code)

Max Activating Token Index: 485

Text #18

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.5867. Min Act: -0.0000

Data Index: 1449391 (Python Code)

Max Activating Token Index: 810

Text #19

Max Range: 2.5994. Min Range: -2.5994

Max Act: 1.6578. Min Act: -0.0000

Data Index: 366727 (C4 (Web Text))

Max Activating Token Index: 244