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

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

Neuron 4057 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.7031. Min Act: -0.0000

Data Index: 964026 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.5530. Min Act: -0.0000

Data Index: 622203 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.5214. Min Act: -0.0000

Data Index: 988759 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1143374 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.5003. Min Act: -0.0000

Data Index: 759578 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.4922. Min Act: -0.0000

Data Index: 190400 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.4617. Min Act: -0.0000

Data Index: 264500 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.4710. Min Act: -0.0000

Data Index: 813795 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.4388. Min Act: -0.0000

Data Index: 396993 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.4404. Min Act: -0.0000

Data Index: 278363 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.4053. Min Act: -0.0000

Data Index: 342909 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1205718 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1337511 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.3905. Min Act: -0.0000

Data Index: 508199 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.3935. Min Act: -0.0000

Data Index: 390900 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.3886. Min Act: -0.0000

Data Index: 174224 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.3980. Min Act: -0.0000

Data Index: 469140 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.4079. Min Act: -0.0000

Data Index: 958838 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.3780. Min Act: -0.0000

Data Index: 133655 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.7031. Min Range: -0.7031

Max Act: 0.3944. Min Act: -0.0000

Data Index: 305355 (C4 (Web Text))

Max Activating Token Index: 778