Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 901 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0457. Min Act: -0.0004

Data Index: 868450 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1084413 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0431. Min Act: -0.0003

Data Index: 570098 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0440. Min Act: -0.0004

Data Index: 540338 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0423. Min Act: -0.0004

Data Index: 110899 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0416. Min Act: -0.0003

Data Index: 180199 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0408. Min Act: -0.0003

Data Index: 78880 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0421. Min Act: -0.0004

Data Index: 24449 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0413. Min Act: -0.0003

Data Index: 457817 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0413. Min Act: -0.0003

Data Index: 212000 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0410. Min Act: -0.0003

Data Index: 587144 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1523099 (Python Code)

Max Activating Token Index: 223

Text #12

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0403. Min Act: -0.0003

Data Index: 635222 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0404. Min Act: -0.0004

Data Index: 687538 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0405. Min Act: -0.0003

Data Index: 272080 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0401. Min Act: -0.0003

Data Index: 629372 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0388. Min Act: -0.0003

Data Index: 808503 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0388. Min Act: -0.0003

Data Index: 717187 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1095765 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0388. Min Act: -0.0003

Data Index: 298950 (C4 (Web Text))

Max Activating Token Index: 824