Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2094 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0001

Data Index: 286181 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0491. Min Act: -0.0001

Data Index: 735028 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0364. Min Act: -0.0001

Data Index: 207444 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0428. Min Act: -0.0002

Data Index: 775420 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1404710 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1584760 (Python Code)

Max Activating Token Index: 159

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0396. Min Act: -0.0002

Data Index: 428105 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0397. Min Act: -0.0001

Data Index: 870850 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0391. Min Act: -0.0001

Data Index: 225545 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0327. Min Act: -0.0002

Data Index: 278868 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1432785 (Python Code)

Max Activating Token Index: 882

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0367. Min Act: -0.0001

Data Index: 673379 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0369. Min Act: -0.0001

Data Index: 480847 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1394254 (Python Code)

Max Activating Token Index: 710

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1129128 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0366. Min Act: -0.0001

Data Index: 265105 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1611484 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0368. Min Act: -0.0001

Data Index: 611998 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0362. Min Act: -0.0002

Data Index: 742418 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0368. Min Act: -0.0002

Data Index: 723092 (C4 (Web Text))

Max Activating Token Index: 131