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

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

Neuron 144 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5937. Min Act: -0.0001

Data Index: 411479 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5274. Min Act: -0.0001

Data Index: 372697 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5471. Min Act: -0.0001

Data Index: 1163952 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5089. Min Act: -0.0001

Data Index: 645971 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4871. Min Act: -0.0001

Data Index: 852336 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4961. Min Act: -0.0001

Data Index: 269704 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4519. Min Act: -0.0001

Data Index: 435521 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4671. Min Act: -0.0001

Data Index: 1228362 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4385. Min Act: -0.0001

Data Index: 767916 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4357. Min Act: -0.0001

Data Index: 362378 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4637. Min Act: -0.0001

Data Index: 106486 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4239. Min Act: -0.0001

Data Index: 836593 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4081. Min Act: -0.0001

Data Index: 600315 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4151. Min Act: -0.0001

Data Index: 107185 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4155. Min Act: -0.0001

Data Index: 811548 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4070. Min Act: -0.0001

Data Index: 64091 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.3678. Min Act: -0.0001

Data Index: 1331235 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.3671. Min Act: -0.0001

Data Index: 669404 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4010. Min Act: -0.0001

Data Index: 707945 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.3896. Min Act: -0.0001

Data Index: 304139 (C4 (Web Text))

Max Activating Token Index: 144