Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1074 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3580. Min Act: -0.0001

Data Index: 557791 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3697. Min Act: -0.0001

Data Index: 517430 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3461. Min Act: -0.0000

Data Index: 222774 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3424. Min Act: -0.0000

Data Index: 4476 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3287. Min Act: -0.0000

Data Index: 701463 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3365. Min Act: -0.0000

Data Index: 341353 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1346287 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3138. Min Act: -0.0000

Data Index: 233442 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3110. Min Act: -0.0001

Data Index: 60132 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3220. Min Act: -0.0000

Data Index: 279980 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3228. Min Act: -0.0001

Data Index: 636586 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3076. Min Act: -0.0000

Data Index: 68938 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3183. Min Act: -0.0001

Data Index: 1078532 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1199465 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3033. Min Act: -0.0001

Data Index: 855899 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3114. Min Act: -0.0000

Data Index: 971676 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3095. Min Act: -0.0001

Data Index: 1326655 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2971. Min Act: -0.0000

Data Index: 72471 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1175286 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2941. Min Act: -0.0000

Data Index: 842988 (C4 (Web Text))

Max Activating Token Index: 981