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

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

Neuron 1512 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: 0.2718. Min Range: -0.2718

Max Act: 0.2718. Min Act: -0.0000

Data Index: 840125 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2631. Min Act: -0.0001

Data Index: 620427 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2513. Min Act: -0.0000

Data Index: 319131 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1207821 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2506. Min Act: -0.0000

Data Index: 978426 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2647. Min Act: -0.0001

Data Index: 1284470 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2494. Min Act: -0.0000

Data Index: 259972 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1236779 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2462. Min Act: -0.0000

Data Index: 372468 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2292. Min Act: -0.0001

Data Index: 9728 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2248. Min Act: -0.0000

Data Index: 849565 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2296. Min Act: -0.0000

Data Index: 727923 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2337. Min Act: -0.0001

Data Index: 425123 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1039097 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2308. Min Act: -0.0000

Data Index: 277774 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2335. Min Act: -0.0000

Data Index: 115420 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2310. Min Act: -0.0000

Data Index: 714250 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1277850 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2227. Min Act: -0.0000

Data Index: 673597 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2126. Min Act: -0.0000

Data Index: 652999 (C4 (Web Text))

Max Activating Token Index: 409