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

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

Neuron 2487 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.9596. Min Act: -0.0001

Data Index: 206050 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.8998. Min Act: -0.0000

Data Index: 671193 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.8279. Min Act: -0.0001

Data Index: 512016 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 2.0239. Min Range: -2.0239

Max Act: 2.0239. Min Act: -0.0001

Data Index: 663835 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.7476. Min Act: -0.0001

Data Index: 541850 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.6847. Min Act: -0.0001

Data Index: 1180259 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.6387. Min Act: -0.0000

Data Index: 1118450 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.5695. Min Act: -0.0000

Data Index: 492925 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.6580. Min Act: -0.0001

Data Index: 1178312 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.5847. Min Act: -0.0000

Data Index: 1140198 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.6074. Min Act: -0.0000

Data Index: 699078 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.5638. Min Act: -0.0001

Data Index: 655847 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.5572. Min Act: -0.0001

Data Index: 321019 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.5033. Min Act: -0.0001

Data Index: 1057490 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.5086. Min Act: -0.0000

Data Index: 1330209 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.4996. Min Act: -0.0000

Data Index: 134045 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.5428. Min Act: -0.0001

Data Index: 917410 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.5426. Min Act: -0.0001

Data Index: 578757 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.5311. Min Act: -0.0001

Data Index: 1125330 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 2.0239. Min Range: -2.0239

Max Act: 1.5444. Min Act: -0.0001

Data Index: 1190391 (C4 (Web Text))

Max Activating Token Index: 142