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

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

Neuron 3764 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0726. Min Act: -0.0001

Data Index: 744417 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0550. Min Act: -0.0001

Data Index: 543862 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0493. Min Act: -0.0001

Data Index: 40993 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0440. Min Act: -0.0001

Data Index: 52238 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0466. Min Act: -0.0001

Data Index: 407080 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0433. Min Act: -0.0001

Data Index: 726913 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1300911 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1185007 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0375. Min Act: -0.0001

Data Index: 542380 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1296530 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1152018 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0367. Min Act: -0.0001

Data Index: 128139 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0357. Min Act: -0.0001

Data Index: 91709 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0330. Min Act: -0.0001

Data Index: 373281 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0364. Min Act: -0.0001

Data Index: 763109 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0347. Min Act: -0.0001

Data Index: 981481 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1182681 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0339. Min Act: -0.0001

Data Index: 578952 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0326. Min Act: -0.0001

Data Index: 370053 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1099241 (C4 (Web Text))

Max Activating Token Index: 341