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

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

Neuron 4464 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3407. Min Act: -0.0000

Data Index: 840771 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1128603 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2854. Min Act: -0.0000

Data Index: 872450 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2903. Min Act: -0.0001

Data Index: 374606 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2945. Min Act: -0.0001

Data Index: 1108816 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2666. Min Act: -0.0001

Data Index: 84673 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2649. Min Act: -0.0001

Data Index: 285206 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1259791 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2556. Min Act: -0.0000

Data Index: 95112 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2584. Min Act: -0.0001

Data Index: 935462 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2504. Min Act: -0.0000

Data Index: 480309 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2575. Min Act: -0.0001

Data Index: 559296 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1236533 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2451. Min Act: -0.0000

Data Index: 606909 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2359. Min Act: -0.0000

Data Index: 924173 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2449. Min Act: -0.0000

Data Index: 649831 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2339. Min Act: -0.0000

Data Index: 377569 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2420. Min Act: -0.0001

Data Index: 972176 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2376. Min Act: -0.0000

Data Index: 215273 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1312700 (C4 (Web Text))

Max Activating Token Index: 778