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

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

Neuron 3414 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: 1.5775. Min Range: -1.5775

Max Act: 1.5775. Min Act: -0.0000

Data Index: 1555945 (Python Code)

Max Activating Token Index: 384

Text #1

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.4906. Min Act: -0.0000

Data Index: 1405935 (Python Code)

Max Activating Token Index: 489

Text #2

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.4109. Min Act: -0.0000

Data Index: 299396 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.5329. Min Act: -0.0000

Data Index: 1422234 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.3039. Min Act: -0.0000

Data Index: 383448 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.3368. Min Act: -0.0000

Data Index: 1513513 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1506211 (Python Code)

Max Activating Token Index: 219

Text #7

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.2669. Min Act: -0.0000

Data Index: 617267 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1331506 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.2464. Min Act: -0.0000

Data Index: 40245 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.2526. Min Act: -0.0000

Data Index: 693889 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1423781 (Python Code)

Max Activating Token Index: 136

Text #12

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1062383 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1241102 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.2592. Min Act: -0.0000

Data Index: 776435 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.1485. Min Act: -0.0000

Data Index: 829646 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1457848 (Python Code)

Max Activating Token Index: 259

Text #17

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.1397. Min Act: -0.0000

Data Index: 983849 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.2035. Min Act: -0.0000

Data Index: 177174 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 1.5775. Min Range: -1.5775

Max Act: 1.0646. Min Act: -0.0000

Data Index: 1552931 (Python Code)

Max Activating Token Index: 1008