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

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

Neuron 788 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.8350. Min Act: -0.0002

Data Index: 860351 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.4725. Min Act: -0.0002

Data Index: 578108 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.2733. Min Act: -0.0002

Data Index: 903601 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.2219. Min Act: -0.0002

Data Index: 517728 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.0822. Min Act: -0.0002

Data Index: 307846 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.1348. Min Act: -0.0002

Data Index: 910677 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.2843. Min Act: -0.0002

Data Index: 1041542 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.1073. Min Act: -0.0002

Data Index: 507240 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.3493. Min Act: -0.0002

Data Index: 1235142 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.0450. Min Act: -0.0002

Data Index: 834751 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.1078. Min Act: -0.0002

Data Index: 1261311 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.1871. Min Act: -0.0002

Data Index: 1331684 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.1417. Min Act: -0.0002

Data Index: 1229934 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.1844. Min Act: -0.0002

Data Index: 1002395 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 1.8350. Min Range: -1.8350

Max Act: 0.9981. Min Act: -0.0002

Data Index: 672324 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.2040. Min Act: -0.0002

Data Index: 49495 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.2073. Min Act: -0.0002

Data Index: 596859 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.2719. Min Act: -0.0002

Data Index: 1101726 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.1719. Min Act: -0.0002

Data Index: 359345 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 1.8350. Min Range: -1.8350

Max Act: 1.2338. Min Act: -0.0002

Data Index: 425032 (C4 (Web Text))

Max Activating Token Index: 350