Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5993 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0446. Min Act: -0.0000

Data Index: 1503994 (Python Code)

Max Activating Token Index: 1013

Text #1

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0418. Min Act: -0.0000

Data Index: 234260 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1510209 (Python Code)

Max Activating Token Index: 613

Text #3

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0395. Min Act: -0.0000

Data Index: 1411477 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1460434 (Python Code)

Max Activating Token Index: 159

Text #5

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0371. Min Act: -0.0000

Data Index: 1282258 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0366. Min Act: -0.0000

Data Index: 1031774 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1101194 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0399. Min Act: -0.0000

Data Index: 124441 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0362. Min Act: -0.0001

Data Index: 379568 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0385. Min Act: -0.0000

Data Index: 647301 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1124926 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0357. Min Act: -0.0000

Data Index: 261827 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1461957 (Python Code)

Max Activating Token Index: 455

Text #14

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1256079 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0345. Min Act: -0.0000

Data Index: 484980 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0353. Min Act: -0.0000

Data Index: 797372 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0332. Min Act: -0.0000

Data Index: 1331904 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1050744 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0326. Min Act: -0.0000

Data Index: 876970 (C4 (Web Text))

Max Activating Token Index: 39