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

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

Neuron 3327 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0002

Data Index: 908602 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0416. Min Act: -0.0002

Data Index: 391344 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1221292 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1015462 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1215924 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1550295 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0369. Min Act: -0.0002

Data Index: 754698 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0371. Min Act: -0.0002

Data Index: 254104 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1481409 (Python Code)

Max Activating Token Index: 954

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0365. Min Act: -0.0002

Data Index: 418230 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0364. Min Act: -0.0002

Data Index: 807357 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1433708 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0352. Min Act: -0.0002

Data Index: 397872 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1619138 (Python Code)

Max Activating Token Index: 216

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1385815 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1160135 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0355. Min Act: -0.0002

Data Index: 263070 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0354. Min Act: -0.0002

Data Index: 822662 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1613204 (Python Code)

Max Activating Token Index: 276

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0354. Min Act: -0.0002

Data Index: 945857 (C4 (Web Text))

Max Activating Token Index: 711