Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1923 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.5386. Min Act: -0.0001

Data Index: 563555 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.4265. Min Act: -0.0001

Data Index: 420571 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.4529. Min Act: -0.0001

Data Index: 585602 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.4264. Min Act: -0.0001

Data Index: 639082 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3648. Min Act: -0.0001

Data Index: 900515 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3644. Min Act: -0.0001

Data Index: 904746 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.4119. Min Act: -0.0001

Data Index: 1084437 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3981. Min Act: -0.0001

Data Index: 373756 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3513. Min Act: -0.0001

Data Index: 1165429 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3134. Min Act: -0.0001

Data Index: 32272 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3154. Min Act: -0.0001

Data Index: 122951 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3499. Min Act: -0.0001

Data Index: 820199 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3340. Min Act: -0.0001

Data Index: 1578729 (Python Code)

Max Activating Token Index: 902

Text #13

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3138. Min Act: -0.0001

Data Index: 418759 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3124. Min Act: -0.0001

Data Index: 150904 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3498. Min Act: -0.0001

Data Index: 1345656 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2258. Min Act: -0.0001

Data Index: 291284 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2974. Min Act: -0.0001

Data Index: 161063 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3558. Min Act: -0.0001

Data Index: 1350574 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3135. Min Act: -0.0001

Data Index: 872338 (C4 (Web Text))

Max Activating Token Index: 665