Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 558 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.9139. Min Act: -0.0001

Data Index: 263519 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.7226. Min Act: -0.0001

Data Index: 424286 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6463. Min Act: -0.0001

Data Index: 753547 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.7307. Min Act: -0.0001

Data Index: 559511 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6775. Min Act: -0.0001

Data Index: 653594 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6331. Min Act: -0.0001

Data Index: 119456 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6352. Min Act: -0.0001

Data Index: 359955 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6171. Min Act: -0.0001

Data Index: 23478 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6246. Min Act: -0.0001

Data Index: 306765 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5778. Min Act: -0.0001

Data Index: 1218659 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5765. Min Act: -0.0001

Data Index: 610830 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6306. Min Act: -0.0001

Data Index: 575785 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5937. Min Act: -0.0001

Data Index: 446002 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.7401. Min Act: -0.0001

Data Index: 364308 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5746. Min Act: -0.0001

Data Index: 222199 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5978. Min Act: -0.0001

Data Index: 454664 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5702. Min Act: -0.0001

Data Index: 11899 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5320. Min Act: -0.0001

Data Index: 860936 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5682. Min Act: -0.0001

Data Index: 908479 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5306. Min Act: -0.0001

Data Index: 99187 (C4 (Web Text))

Max Activating Token Index: 1017