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

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

Neuron 5596 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6942. Min Act: -0.0000

Data Index: 395805 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6114. Min Act: -0.0000

Data Index: 378567 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6026. Min Act: -0.0000

Data Index: 558237 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5652. Min Act: -0.0000

Data Index: 827384 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6504. Min Act: -0.0000

Data Index: 80658 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1189550 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1227516 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5601. Min Act: -0.0000

Data Index: 658050 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5363. Min Act: -0.0000

Data Index: 779682 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5541. Min Act: -0.0000

Data Index: 772277 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1099390 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5731. Min Act: -0.0000

Data Index: 868082 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5165. Min Act: -0.0000

Data Index: 283424 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1062561 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4674. Min Act: -0.0000

Data Index: 483144 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4467. Min Act: -0.0000

Data Index: 867310 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4666. Min Act: -0.0000

Data Index: 29488 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1437899 (Python Code)

Max Activating Token Index: 190

Text #18

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1413276 (Python Code)

Max Activating Token Index: 670

Text #19

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1361089 (Python Code)

Max Activating Token Index: 614