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

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

Neuron 2847 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: 3.0591. Min Range: -3.0591

Max Act: 2.8043. Min Act: -0.0000

Data Index: 232714 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.7345. Min Act: -0.0000

Data Index: 114749 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.8178. Min Act: -0.0000

Data Index: 843829 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.9364. Min Act: -0.0000

Data Index: 1139791 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 3.0591. Min Range: -3.0591

Max Act: 3.0591. Min Act: -0.0000

Data Index: 369232 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.9011. Min Act: -0.0000

Data Index: 230528 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.6514. Min Act: -0.0000

Data Index: 255836 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.4703. Min Act: -0.0000

Data Index: 990998 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.4065. Min Act: -0.0000

Data Index: 682929 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.3769. Min Act: -0.0000

Data Index: 676542 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.4001. Min Act: -0.0000

Data Index: 636457 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.5573. Min Act: -0.0000

Data Index: 607106 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.5853. Min Act: -0.0000

Data Index: 1235225 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.2718. Min Act: -0.0000

Data Index: 772411 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.5345. Min Act: -0.0000

Data Index: 256395 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.2239. Min Act: -0.0000

Data Index: 252960 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.2309. Min Act: -0.0000

Data Index: 1434329 (Python Code)

Max Activating Token Index: 153

Text #17

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.2661. Min Act: -0.0000

Data Index: 328458 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.1970. Min Act: -0.0000

Data Index: 1292708 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 3.0591. Min Range: -3.0591

Max Act: 2.0440. Min Act: -0.0000

Data Index: 903399 (C4 (Web Text))

Max Activating Token Index: 969