Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4509 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.1930. Min Range: -4.1930

Max Act: 4.1930. Min Act: -0.0000

Data Index: 1016937 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.8550. Min Act: -0.0000

Data Index: 425433 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.7692. Min Act: -0.0000

Data Index: 890914 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.7090. Min Act: -0.0000

Data Index: 227266 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.6478. Min Act: -0.0000

Data Index: 1064864 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.6588. Min Act: -0.0000

Data Index: 1173505 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.6389. Min Act: -0.0000

Data Index: 319084 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.5804. Min Act: -0.0000

Data Index: 202141 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.5456. Min Act: -0.0000

Data Index: 1240179 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.2193. Min Act: -0.0000

Data Index: 780095 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.3585. Min Act: -0.0000

Data Index: 391948 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.5158. Min Act: -0.0000

Data Index: 750276 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.3472. Min Act: -0.0001

Data Index: 827754 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.6432. Min Act: -0.0000

Data Index: 429559 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.3189. Min Act: -0.0000

Data Index: 1244987 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.4688. Min Act: -0.0000

Data Index: 83517 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.3093. Min Act: -0.0000

Data Index: 717260 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.4694. Min Act: -0.0000

Data Index: 1246708 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.4366. Min Act: -0.0000

Data Index: 1247718 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 4.1930. Min Range: -4.1930

Max Act: 3.4019. Min Act: -0.0001

Data Index: 1233761 (C4 (Web Text))

Max Activating Token Index: 46