Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 479 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.8266. Min Act: -0.0000

Data Index: 794723 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.7357. Min Act: -0.0000

Data Index: 306570 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.5993. Min Act: -0.0000

Data Index: 226029 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.5266. Min Act: -0.0000

Data Index: 653682 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.3872. Min Act: -0.0000

Data Index: 805417 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.4919. Min Act: -0.0000

Data Index: 633354 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.4967. Min Act: -0.0000

Data Index: 149848 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.6410. Min Act: -0.0000

Data Index: 139977 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.4472. Min Act: -0.0000

Data Index: 1310981 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1000808 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1230899 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.4184. Min Act: -0.0000

Data Index: 161395 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1207291 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1239876 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.2519. Min Act: -0.0000

Data Index: 331565 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.2790. Min Act: -0.0000

Data Index: 923134 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.2561. Min Act: -0.0000

Data Index: 886872 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.3061. Min Act: -0.0000

Data Index: 1268848 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.2413. Min Act: -0.0000

Data Index: 282925 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.3159. Min Act: -0.0000

Data Index: 656943 (C4 (Web Text))

Max Activating Token Index: 939