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

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

Neuron 2077 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1283204 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2803. Min Act: -0.0000

Data Index: 794579 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2723. Min Act: -0.0001

Data Index: 474670 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2651. Min Act: -0.0001

Data Index: 844902 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2735. Min Act: -0.0001

Data Index: 187221 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2519. Min Act: -0.0001

Data Index: 1213494 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2468. Min Act: -0.0001

Data Index: 704231 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2640. Min Act: -0.0000

Data Index: 387113 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1272568 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2466. Min Act: -0.0001

Data Index: 470012 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1270356 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2630. Min Act: -0.0000

Data Index: 794929 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1299208 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1013341 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2430. Min Act: -0.0001

Data Index: 667825 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2336. Min Act: -0.0000

Data Index: 744567 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2319. Min Act: -0.0001

Data Index: 239485 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2439. Min Act: -0.0001

Data Index: 54118 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2293. Min Act: -0.0001

Data Index: 253518 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2350. Min Act: -0.0001

Data Index: 246834 (C4 (Web Text))

Max Activating Token Index: 336