Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2919 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5497. Min Act: -0.0001

Data Index: 1245523 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5289. Min Act: -0.0001

Data Index: 921926 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5151. Min Act: -0.0001

Data Index: 637835 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5188. Min Act: -0.0001

Data Index: 866098 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5281. Min Act: -0.0001

Data Index: 549165 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5097. Min Act: -0.0001

Data Index: 625782 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4985. Min Act: -0.0001

Data Index: 366880 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4523. Min Act: -0.0001

Data Index: 1175654 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4644. Min Act: -0.0001

Data Index: 1141659 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4564. Min Act: -0.0001

Data Index: 443679 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4369. Min Act: -0.0001

Data Index: 1454197 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4520. Min Act: -0.0001

Data Index: 59839 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4365. Min Act: -0.0001

Data Index: 969127 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4482. Min Act: -0.0001

Data Index: 437318 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4424. Min Act: -0.0001

Data Index: 1327633 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4273. Min Act: -0.0001

Data Index: 1533330 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4237. Min Act: -0.0001

Data Index: 694903 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4476. Min Act: -0.0001

Data Index: 236523 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4293. Min Act: -0.0001

Data Index: 123545 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4175. Min Act: -0.0001

Data Index: 799390 (C4 (Web Text))

Max Activating Token Index: 619