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

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

Neuron 3835 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4495. Min Act: -0.0000

Data Index: 852573 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4093. Min Act: -0.0000

Data Index: 147552 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4008. Min Act: -0.0000

Data Index: 349391 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3984. Min Act: -0.0000

Data Index: 323083 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1052037 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3839. Min Act: -0.0000

Data Index: 807091 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3701. Min Act: -0.0000

Data Index: 603373 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3671. Min Act: -0.0000

Data Index: 83185 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1100371 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1187457 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1188069 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3230. Min Act: -0.0000

Data Index: 465366 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3080. Min Act: -0.0000

Data Index: 532430 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1202982 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1240992 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3147. Min Act: -0.0000

Data Index: 619837 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3027. Min Act: -0.0000

Data Index: 222071 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3219. Min Act: -0.0000

Data Index: 287037 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3018. Min Act: -0.0000

Data Index: 784989 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2970. Min Act: -0.0000

Data Index: 145908 (C4 (Web Text))

Max Activating Token Index: 567