Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1736 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.9230. Min Act: -0.0000

Data Index: 1557194 (Python Code)

Max Activating Token Index: 1006

Text #1

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.5579. Min Act: -0.0000

Data Index: 1466464 (Python Code)

Max Activating Token Index: 939

Text #2

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.6380. Min Act: -0.0000

Data Index: 1365176 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.6006. Min Act: -0.0000

Data Index: 1463933 (Python Code)

Max Activating Token Index: 470

Text #4

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.6053. Min Act: -0.0000

Data Index: 1545537 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.4682. Min Act: -0.0000

Data Index: 1611261 (Python Code)

Max Activating Token Index: 533

Text #6

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.4570. Min Act: -0.0000

Data Index: 1545145 (Python Code)

Max Activating Token Index: 789

Text #7

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.4928. Min Act: -0.0000

Data Index: 1435581 (Python Code)

Max Activating Token Index: 636

Text #8

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.3285. Min Act: -0.0000

Data Index: 1431329 (Python Code)

Max Activating Token Index: 351

Text #9

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.5577. Min Act: -0.0000

Data Index: 1548541 (Python Code)

Max Activating Token Index: 554

Text #10

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.4301. Min Act: -0.0000

Data Index: 1556315 (Python Code)

Max Activating Token Index: 611

Text #11

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.3851. Min Act: -0.0000

Data Index: 1527755 (Python Code)

Max Activating Token Index: 451

Text #12

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.3838. Min Act: -0.0000

Data Index: 1502777 (Python Code)

Max Activating Token Index: 467

Text #13

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.3517. Min Act: -0.0000

Data Index: 1457181 (Python Code)

Max Activating Token Index: 75

Text #14

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.3329. Min Act: -0.0000

Data Index: 1642877 (Python Code)

Max Activating Token Index: 566

Text #15

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.3206. Min Act: -0.0000

Data Index: 1465017 (Python Code)

Max Activating Token Index: 696

Text #16

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.3213. Min Act: -0.0000

Data Index: 1418376 (Python Code)

Max Activating Token Index: 777

Text #17

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.3036. Min Act: -0.0000

Data Index: 1416065 (Python Code)

Max Activating Token Index: 771

Text #18

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.2932. Min Act: -0.0000

Data Index: 1573593 (Python Code)

Max Activating Token Index: 681

Text #19

Max Range: 2.9230. Min Range: -2.9230

Max Act: 2.2576. Min Act: -0.0000

Data Index: 1372233 (Python Code)

Max Activating Token Index: 469