Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4524 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1174. Min Range: -2.1174

Max Act: 2.0522. Min Act: -0.0000

Data Index: 778519 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 2.1174. Min Range: -2.1174

Max Act: 2.0870. Min Act: -0.0000

Data Index: 567160 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.9028. Min Act: -0.0000

Data Index: 561070 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 2.1174. Min Range: -2.1174

Max Act: 2.1174. Min Act: -0.0000

Data Index: 1275684 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.5883. Min Act: -0.0000

Data Index: 710134 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.7250. Min Act: -0.0000

Data Index: 5 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.6313. Min Act: -0.0000

Data Index: 454407 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.7244. Min Act: -0.0000

Data Index: 260780 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.6016. Min Act: -0.0000

Data Index: 1249846 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.7363. Min Act: -0.0000

Data Index: 1018953 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.4860. Min Act: -0.0000

Data Index: 465373 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1169941 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.4513. Min Act: -0.0000

Data Index: 488247 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.6813. Min Act: -0.0000

Data Index: 1199395 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1203098 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.5887. Min Act: -0.0000

Data Index: 191178 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.4689. Min Act: -0.0000

Data Index: 346893 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.4508. Min Act: -0.0000

Data Index: 1253152 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.3656. Min Act: -0.0000

Data Index: 785204 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 2.1174. Min Range: -2.1174

Max Act: 1.4386. Min Act: -0.0000

Data Index: 980006 (C4 (Web Text))

Max Activating Token Index: 544