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

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

Neuron 4821 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.4034. Min Act: -0.0000

Data Index: 681462 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1120653 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3022. Min Act: -0.0000

Data Index: 899110 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3389. Min Act: -0.0000

Data Index: 296345 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1299476 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2945. Min Act: -0.0000

Data Index: 615514 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1049532 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2479. Min Act: -0.0000

Data Index: 131640 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2557. Min Act: -0.0000

Data Index: 835095 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2430. Min Act: 0.0000

Data Index: 1531060 (Python Code)

Max Activating Token Index: 881

Text #10

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2477. Min Act: -0.0000

Data Index: 619882 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2492. Min Act: -0.0000

Data Index: 395574 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2309. Min Act: -0.0000

Data Index: 429890 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2286. Min Act: -0.0000

Data Index: 230281 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2560. Min Act: -0.0000

Data Index: 713416 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2448. Min Act: -0.0000

Data Index: 985685 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2388. Min Act: -0.0000

Data Index: 666004 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2460. Min Act: -0.0000

Data Index: 650223 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2435. Min Act: -0.0000

Data Index: 897540 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2255. Min Act: -0.0000

Data Index: 51188 (C4 (Web Text))

Max Activating Token Index: 937