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

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

Neuron 4280 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0002

Data Index: 864529 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0507. Min Act: -0.0003

Data Index: 458905 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1007973 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0428. Min Act: -0.0003

Data Index: 682232 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0416. Min Act: -0.0003

Data Index: 29507 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0412. Min Act: -0.0003

Data Index: 250469 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0402. Min Act: -0.0003

Data Index: 195424 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0410. Min Act: -0.0003

Data Index: 974515 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0406. Min Act: -0.0003

Data Index: 39238 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0394. Min Act: -0.0003

Data Index: 193987 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1146134 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0338. Min Act: -0.0003

Data Index: 450151 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0402. Min Act: -0.0003

Data Index: 406004 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1203618 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1344553 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0364. Min Act: -0.0003

Data Index: 392956 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0376. Min Act: -0.0003

Data Index: 155136 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1085552 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0384. Min Act: -0.0002

Data Index: 995650 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0358. Min Act: -0.0003

Data Index: 540533 (C4 (Web Text))

Max Activating Token Index: 246