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

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

Neuron 3651 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.7867. Min Act: -0.0000

Data Index: 882318 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1217451 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.7426. Min Act: -0.0001

Data Index: 1273833 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.7450. Min Act: -0.0001

Data Index: 974911 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.7414. Min Act: -0.0000

Data Index: 805746 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1343337 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6779. Min Act: -0.0001

Data Index: 163239 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6760. Min Act: -0.0000

Data Index: 463359 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6458. Min Act: -0.0001

Data Index: 792204 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6405. Min Act: -0.0000

Data Index: 189314 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6361. Min Act: -0.0000

Data Index: 887471 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6523. Min Act: -0.0000

Data Index: 952940 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6354. Min Act: -0.0000

Data Index: 802903 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6526. Min Act: -0.0000

Data Index: 486332 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6348. Min Act: -0.0000

Data Index: 583068 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1251256 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1081622 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5792. Min Act: -0.0001

Data Index: 1206826 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5858. Min Act: -0.0000

Data Index: 10775 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5876. Min Act: -0.0001

Data Index: 811394 (C4 (Web Text))

Max Activating Token Index: 433