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

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

Neuron 664 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.7185. Min Act: -0.0000

Data Index: 147205 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.5617. Min Act: -0.0000

Data Index: 679827 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.5902. Min Act: -0.0000

Data Index: 39723 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.4907. Min Act: -0.0000

Data Index: 331540 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.4479. Min Act: -0.0000

Data Index: 269245 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.4397. Min Act: -0.0000

Data Index: 346683 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.3321. Min Act: -0.0000

Data Index: 145420 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.4216. Min Act: -0.0000

Data Index: 49939 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.3302. Min Act: -0.0000

Data Index: 1236643 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.1947. Min Act: -0.0000

Data Index: 185457 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.2895. Min Act: -0.0000

Data Index: 15273 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.1464. Min Act: -0.0000

Data Index: 548100 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.4654. Min Act: -0.0000

Data Index: 182627 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.0408. Min Act: -0.0000

Data Index: 664420 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.1951. Min Act: -0.0000

Data Index: 466263 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.3062. Min Act: -0.0000

Data Index: 1123403 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.2971. Min Act: -0.0000

Data Index: 1288981 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.1540. Min Act: -0.0000

Data Index: 257666 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.1486. Min Act: -0.0000

Data Index: 264897 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 2.7185. Min Range: -2.7185

Max Act: 2.0305. Min Act: -0.0000

Data Index: 610230 (C4 (Web Text))

Max Activating Token Index: 690