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

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

Neuron 457 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4116. Min Range: -7.4116

Max Act: 7.3297. Min Act: -0.0001

Data Index: 506586 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 7.4116. Min Range: -7.4116

Max Act: 7.0571. Min Act: -0.0001

Data Index: 922330 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.8543. Min Act: -0.0001

Data Index: 333585 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 7.4116. Min Range: -7.4116

Max Act: 7.1467. Min Act: -0.0001

Data Index: 555015 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 7.4116. Min Range: -7.4116

Max Act: 7.1419. Min Act: -0.0001

Data Index: 1328750 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 7.4116. Min Range: -7.4116

Max Act: 7.0785. Min Act: -0.0001

Data Index: 646068 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 7.4116. Min Range: -7.4116

Max Act: 7.2536. Min Act: -0.0001

Data Index: 144076 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.8933. Min Act: -0.0001

Data Index: 774442 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 7.4116. Min Range: -7.4116

Max Act: 7.4116. Min Act: -0.0001

Data Index: 1141226 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.4428. Min Act: -0.0001

Data Index: 770971 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 7.4116. Min Range: -7.4116

Max Act: 7.1259. Min Act: -0.0001

Data Index: 590391 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.9150. Min Act: -0.0001

Data Index: 691765 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.7044. Min Act: -0.0001

Data Index: 85062 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.7261. Min Act: -0.0001

Data Index: 566735 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.6990. Min Act: -0.0001

Data Index: 63005 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.6963. Min Act: -0.0001

Data Index: 680918 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.8434. Min Act: -0.0001

Data Index: 5694 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.4864. Min Act: -0.0001

Data Index: 594479 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.6661. Min Act: -0.0001

Data Index: 1343939 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 7.4116. Min Range: -7.4116

Max Act: 6.7944. Min Act: -0.0001

Data Index: 113613 (C4 (Web Text))

Max Activating Token Index: 502