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

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

Neuron 4832 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5698. Min Range: -6.5698

Max Act: 6.5698. Min Act: -0.0000

Data Index: 563768 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 6.5698. Min Range: -6.5698

Max Act: 6.2483. Min Act: -0.0000

Data Index: 1315164 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 6.5698. Min Range: -6.5698

Max Act: 6.2643. Min Act: -0.0000

Data Index: 71688 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 6.5698. Min Range: -6.5698

Max Act: 6.0894. Min Act: -0.0000

Data Index: 328228 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 6.5698. Min Range: -6.5698

Max Act: 6.0656. Min Act: -0.0000

Data Index: 402130 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 6.5698. Min Range: -6.5698

Max Act: 6.1044. Min Act: -0.0000

Data Index: 1280086 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.8521. Min Act: -0.0000

Data Index: 90498 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.8387. Min Act: -0.0000

Data Index: 734063 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.8288. Min Act: -0.0000

Data Index: 611256 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.5715. Min Act: -0.0000

Data Index: 486726 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.6919. Min Act: -0.0000

Data Index: 1164225 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.5050. Min Act: -0.0000

Data Index: 1015344 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.2571. Min Act: -0.0000

Data Index: 873082 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.4243. Min Act: -0.0000

Data Index: 1259201 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.6289. Min Act: -0.0000

Data Index: 857233 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.4028. Min Act: -0.0000

Data Index: 1015372 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.2127. Min Act: -0.0000

Data Index: 896511 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.3681. Min Act: -0.0000

Data Index: 693698 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.3562. Min Act: 0.0000

Data Index: 1184 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 6.5698. Min Range: -6.5698

Max Act: 5.3426. Min Act: -0.0000

Data Index: 95051 (C4 (Web Text))

Max Activating Token Index: 210