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

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

Neuron 2614 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: 2.7146. Min Range: -2.7146

Max Act: 2.7146. Min Act: -0.0000

Data Index: 346525 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 2.7146. Min Range: -2.7146

Max Act: 2.4050. Min Act: -0.0000

Data Index: 358316 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 2.7146. Min Range: -2.7146

Max Act: 2.3553. Min Act: -0.0000

Data Index: 377359 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.8380. Min Act: -0.0000

Data Index: 728478 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.6635. Min Act: -0.0000

Data Index: 754737 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.6211. Min Act: -0.0000

Data Index: 538059 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.8018. Min Act: -0.0000

Data Index: 1056168 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.7054. Min Act: -0.0000

Data Index: 563757 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.8066. Min Act: -0.0000

Data Index: 353785 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.3356. Min Act: -0.0000

Data Index: 1059450 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.5634. Min Act: -0.0000

Data Index: 1307773 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.5506. Min Act: -0.0000

Data Index: 1325241 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.6513. Min Act: -0.0000

Data Index: 269170 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.5610. Min Act: -0.0000

Data Index: 58030 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.6321. Min Act: -0.0000

Data Index: 1321041 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.6297. Min Act: -0.0000

Data Index: 604634 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.6150. Min Act: -0.0000

Data Index: 751681 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.9915. Min Act: -0.0000

Data Index: 731403 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.4839. Min Act: -0.0000

Data Index: 402632 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 2.7146. Min Range: -2.7146

Max Act: 1.5743. Min Act: -0.0000

Data Index: 313933 (C4 (Web Text))

Max Activating Token Index: 49