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

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

Neuron 1977 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.7299. Min Act: -0.0001

Data Index: 482137 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6352. Min Act: -0.0001

Data Index: 286301 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.5466. Min Act: -0.0001

Data Index: 1052637 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.5599. Min Act: -0.0001

Data Index: 693533 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.5498. Min Act: -0.0001

Data Index: 517547 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4065. Min Act: -0.0001

Data Index: 26042 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.3957. Min Act: -0.0001

Data Index: 364705 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4958. Min Act: -0.0001

Data Index: 509630 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.5758. Min Act: -0.0001

Data Index: 998141 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4529. Min Act: -0.0001

Data Index: 287105 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4513. Min Act: -0.0001

Data Index: 1188543 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4524. Min Act: -0.0001

Data Index: 1129406 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4410. Min Act: -0.0001

Data Index: 575540 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4812. Min Act: -0.0001

Data Index: 815221 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4165. Min Act: -0.0001

Data Index: 551719 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4645. Min Act: -0.0001

Data Index: 829347 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.3863. Min Act: -0.0001

Data Index: 128228 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.3921. Min Act: -0.0001

Data Index: 1106778 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4379. Min Act: -0.0001

Data Index: 807789 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4268. Min Act: -0.0001

Data Index: 620599 (C4 (Web Text))

Max Activating Token Index: 180