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

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

Neuron 5980 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6452. Min Range: -1.6452

Max Act: 1.6452. Min Act: -0.0000

Data Index: 1342618 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 1.6452. Min Range: -1.6452

Max Act: 1.4072. Min Act: -0.0000

Data Index: 1063381 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 1.6452. Min Range: -1.6452

Max Act: 1.4246. Min Act: -0.0000

Data Index: 604210 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 1.6452. Min Range: -1.6452

Max Act: 1.2219. Min Act: -0.0000

Data Index: 749502 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.6452. Min Range: -1.6452

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1289190 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 1.6452. Min Range: -1.6452

Max Act: 1.1715. Min Act: -0.0000

Data Index: 683421 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 1.6452. Min Range: -1.6452

Max Act: 1.1288. Min Act: -0.0000

Data Index: 1292419 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1264222 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.8565. Min Act: -0.0000

Data Index: 499504 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.8292. Min Act: -0.0000

Data Index: 314102 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.7557. Min Act: -0.0000

Data Index: 426007 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.7922. Min Act: -0.0000

Data Index: 722711 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.7304. Min Act: -0.0000

Data Index: 849664 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1153606 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1388692 (Python Code)

Max Activating Token Index: 299

Text #15

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1067432 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1340668 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.6135. Min Act: -0.0000

Data Index: 2523 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.6448. Min Act: -0.0000

Data Index: 912077 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 1.6452. Min Range: -1.6452

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1378602 (Python Code)

Max Activating Token Index: 374