Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1598 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1300494 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0472. Min Act: -0.0001

Data Index: 199422 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0448. Min Act: -0.0001

Data Index: 612850 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0399. Min Act: -0.0001

Data Index: 355809 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0420. Min Act: -0.0001

Data Index: 1197929 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0354. Min Act: -0.0001

Data Index: 327425 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0372. Min Act: -0.0001

Data Index: 858653 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0369. Min Act: -0.0001

Data Index: 142427 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0375. Min Act: -0.0001

Data Index: 938077 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0365. Min Act: -0.0001

Data Index: 897194 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0365. Min Act: -0.0001

Data Index: 732662 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0380. Min Act: -0.0001

Data Index: 1237938 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0379. Min Act: -0.0001

Data Index: 835018 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0375. Min Act: -0.0001

Data Index: 901770 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0410. Min Act: -0.0001

Data Index: 904938 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1076876 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0367. Min Act: -0.0001

Data Index: 619215 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0343. Min Act: -0.0001

Data Index: 124534 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1015956 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0346. Min Act: -0.0001

Data Index: 705213 (C4 (Web Text))

Max Activating Token Index: 105