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

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

Neuron 1456 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6936. Min Act: -0.0001

Data Index: 424338 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6087. Min Act: -0.0001

Data Index: 498564 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5451. Min Act: -0.0001

Data Index: 903256 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5933. Min Act: -0.0001

Data Index: 706440 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6155. Min Act: -0.0001

Data Index: 1305940 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5894. Min Act: -0.0001

Data Index: 115272 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5668. Min Act: -0.0001

Data Index: 948449 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5394. Min Act: -0.0001

Data Index: 721199 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5480. Min Act: -0.0001

Data Index: 753961 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5513. Min Act: -0.0001

Data Index: 1071101 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5523. Min Act: -0.0001

Data Index: 513702 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5339. Min Act: -0.0001

Data Index: 566714 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5498. Min Act: -0.0001

Data Index: 396595 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5629. Min Act: -0.0001

Data Index: 365755 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5426. Min Act: -0.0001

Data Index: 794360 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5516. Min Act: -0.0001

Data Index: 1196899 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5396. Min Act: -0.0001

Data Index: 941396 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5190. Min Act: -0.0001

Data Index: 493679 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5379. Min Act: -0.0001

Data Index: 991778 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.4854. Min Act: -0.0001

Data Index: 150185 (C4 (Web Text))

Max Activating Token Index: 668