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

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

Neuron 654 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5551. Min Act: -0.0000

Data Index: 838485 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4901. Min Act: -0.0000

Data Index: 249058 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5521. Min Act: -0.0000

Data Index: 45700 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5022. Min Act: -0.0000

Data Index: 689613 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4587. Min Act: -0.0000

Data Index: 921156 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4531. Min Act: -0.0000

Data Index: 941619 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4585. Min Act: -0.0000

Data Index: 934285 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4671. Min Act: -0.0000

Data Index: 581637 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4683. Min Act: -0.0000

Data Index: 965650 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4497. Min Act: -0.0000

Data Index: 614822 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1051141 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4412. Min Act: -0.0000

Data Index: 63086 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4187. Min Act: -0.0000

Data Index: 716213 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1358178 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4179. Min Act: -0.0000

Data Index: 926092 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4296. Min Act: -0.0000

Data Index: 757011 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4365. Min Act: 0.0000

Data Index: 1262279 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4112. Min Act: -0.0000

Data Index: 52162 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1353605 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.4062. Min Act: -0.0000

Data Index: 547054 (C4 (Web Text))

Max Activating Token Index: 558