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

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

Neuron 1058 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.6543. Min Act: -0.0000

Data Index: 399195 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5560. Min Act: -0.0000

Data Index: 749800 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4961. Min Act: -0.0001

Data Index: 1206515 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4933. Min Act: -0.0001

Data Index: 176303 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4612. Min Act: -0.0000

Data Index: 704265 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4478. Min Act: -0.0000

Data Index: 432156 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4630. Min Act: -0.0000

Data Index: 695101 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4327. Min Act: -0.0001

Data Index: 84435 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4051. Min Act: -0.0000

Data Index: 179568 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4464. Min Act: -0.0000

Data Index: 77214 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4403. Min Act: -0.0000

Data Index: 985599 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1064123 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4332. Min Act: -0.0000

Data Index: 783483 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1157564 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4482. Min Act: -0.0001

Data Index: 68262 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.3616. Min Act: -0.0000

Data Index: 707361 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.3708. Min Act: -0.0000

Data Index: 775508 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.3635. Min Act: -0.0000

Data Index: 186863 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1115219 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.3698. Min Act: -0.0000

Data Index: 950685 (C4 (Web Text))

Max Activating Token Index: 78