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

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

Neuron 4324 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2825. Min Range: -4.2825

Max Act: 4.2825. Min Act: -0.0000

Data Index: 591537 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 4.2825. Min Range: -4.2825

Max Act: 4.0425. Min Act: -0.0000

Data Index: 124490 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 4.2825. Min Range: -4.2825

Max Act: 4.1694. Min Act: -0.0000

Data Index: 107587 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 4.2825. Min Range: -4.2825

Max Act: 4.0222. Min Act: -0.0000

Data Index: 1352747 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.8266. Min Act: -0.0000

Data Index: 713481 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.4478. Min Act: -0.0000

Data Index: 412097 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.7271. Min Act: -0.0000

Data Index: 1345222 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.3677. Min Act: -0.0000

Data Index: 159366 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.3538. Min Act: -0.0000

Data Index: 1107954 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.3212. Min Act: -0.0000

Data Index: 619340 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.4134. Min Act: -0.0000

Data Index: 329573 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.4135. Min Act: -0.0000

Data Index: 333541 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.0552. Min Act: -0.0000

Data Index: 1300070 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.1412. Min Act: -0.0000

Data Index: 332451 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.2885. Min Act: -0.0000

Data Index: 1350578 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.0418. Min Act: -0.0000

Data Index: 1183284 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.1525. Min Act: -0.0000

Data Index: 768105 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 4.2825. Min Range: -4.2825

Max Act: 3.1300. Min Act: -0.0000

Data Index: 1203476 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 4.2825. Min Range: -4.2825

Max Act: 2.8164. Min Act: -0.0000

Data Index: 12448 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 4.2825. Min Range: -4.2825

Max Act: 2.9147. Min Act: -0.0000

Data Index: 100604 (C4 (Web Text))

Max Activating Token Index: 865