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

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

Neuron 580 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5434. Min Act: -0.0000

Data Index: 62750 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3456. Min Act: -0.0000

Data Index: 23700 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3607. Min Act: 0.0001

Data Index: 826074 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1300449 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1062835 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3461. Min Act: -0.0000

Data Index: 721116 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3463. Min Act: -0.0000

Data Index: 712233 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1043164 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3438. Min Act: -0.0000

Data Index: 815046 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3554. Min Act: -0.0000

Data Index: 935721 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3423. Min Act: -0.0000

Data Index: 298086 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3253. Min Act: -0.0000

Data Index: 970587 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3266. Min Act: -0.0000

Data Index: 423758 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3408. Min Act: -0.0000

Data Index: 506048 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3489. Min Act: -0.0000

Data Index: 739849 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3370. Min Act: -0.0000

Data Index: 793814 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3429. Min Act: -0.0000

Data Index: 660030 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3342. Min Act: -0.0000

Data Index: 650985 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3190. Min Act: -0.0000

Data Index: 479093 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3373. Min Act: -0.0000

Data Index: 985578 (C4 (Web Text))

Max Activating Token Index: 291