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

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

Neuron 2146 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.6411. Min Act: -0.0000

Data Index: 770773 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1250656 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4621. Min Act: -0.0000

Data Index: 522827 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4026. Min Act: -0.0000

Data Index: 62922 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1603742 (Python Code)

Max Activating Token Index: 897

Text #5

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1585415 (Python Code)

Max Activating Token Index: 475

Text #6

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1154298 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3575. Min Act: -0.0000

Data Index: 527947 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1314358 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3443. Min Act: -0.0000

Data Index: 950216 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3521. Min Act: -0.0000

Data Index: 757276 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3265. Min Act: -0.0000

Data Index: 449273 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3168. Min Act: -0.0000

Data Index: 37635 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3220. Min Act: -0.0000

Data Index: 869875 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3218. Min Act: -0.0000

Data Index: 705007 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1595160 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3072. Min Act: -0.0000

Data Index: 219904 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1516576 (Python Code)

Max Activating Token Index: 674

Text #18

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.3107. Min Act: -0.0000

Data Index: 477626 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.2959. Min Act: -0.0000

Data Index: 698177 (C4 (Web Text))

Max Activating Token Index: 639