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

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

Neuron 3535 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: 1.3614. Min Range: -1.3614

Max Act: 1.3614. Min Act: -0.0000

Data Index: 107978 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.2049. Min Act: -0.0000

Data Index: 955286 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.3106. Min Act: -0.0000

Data Index: 759144 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.2124. Min Act: -0.0000

Data Index: 194513 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.2119. Min Act: -0.0000

Data Index: 871963 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.8703. Min Act: -0.0000

Data Index: 132484 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.1238. Min Act: -0.0000

Data Index: 591105 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.1288. Min Act: -0.0000

Data Index: 722424 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.1504. Min Act: -0.0000

Data Index: 939321 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0740. Min Act: -0.0000

Data Index: 614956 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0878. Min Act: -0.0000

Data Index: 695190 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.1098. Min Act: -0.0000

Data Index: 1158742 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.8932. Min Act: -0.0000

Data Index: 362806 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0793. Min Act: -0.0000

Data Index: 324108 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0521. Min Act: -0.0000

Data Index: 626257 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0420. Min Act: -0.0000

Data Index: 1028748 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.9407. Min Act: -0.0000

Data Index: 850190 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0411. Min Act: -0.0000

Data Index: 449591 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0071. Min Act: -0.0000

Data Index: 1335086 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0076. Min Act: -0.0000

Data Index: 346441 (C4 (Web Text))

Max Activating Token Index: 87