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

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

Neuron 1601 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.3502. Min Act: -0.0000

Data Index: 831771 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1095146 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2895. Min Act: -0.0000

Data Index: 348561 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2933. Min Act: -0.0000

Data Index: 895398 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1397030 (Python Code)

Max Activating Token Index: 364

Text #5

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2446. Min Act: -0.0000

Data Index: 793579 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1376481 (Python Code)

Max Activating Token Index: 175

Text #7

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1362653 (Python Code)

Max Activating Token Index: 528

Text #8

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1447220 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1574885 (Python Code)

Max Activating Token Index: 733

Text #10

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2598. Min Act: -0.0000

Data Index: 637560 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1201278 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1083208 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1186221 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.3004. Min Act: -0.0000

Data Index: 4059 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2476. Min Act: -0.0000

Data Index: 192879 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1111608 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2310. Min Act: -0.0000

Data Index: 750254 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1331165 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.3502. Min Range: -0.3502

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1068266 (C4 (Web Text))

Max Activating Token Index: 759