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

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

Neuron 3372 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: 0.4493. Min Range: -0.4493

Max Act: 0.4493. Min Act: -0.0000

Data Index: 784207 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1100235 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4400. Min Act: -0.0000

Data Index: 690458 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4094. Min Act: -0.0000

Data Index: 550944 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4143. Min Act: -0.0001

Data Index: 921383 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4275. Min Act: -0.0000

Data Index: 755723 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4165. Min Act: -0.0001

Data Index: 231471 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3909. Min Act: -0.0001

Data Index: 605817 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3865. Min Act: -0.0001

Data Index: 688349 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1248761 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3971. Min Act: -0.0000

Data Index: 589376 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1211384 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3942. Min Act: -0.0001

Data Index: 682764 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3708. Min Act: -0.0001

Data Index: 685385 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3780. Min Act: -0.0000

Data Index: 89761 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3637. Min Act: -0.0000

Data Index: 20347 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3742. Min Act: -0.0001

Data Index: 895386 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3601. Min Act: -0.0000

Data Index: 274406 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3573. Min Act: -0.0001

Data Index: 386177 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3819. Min Act: -0.0000

Data Index: 36356 (C4 (Web Text))

Max Activating Token Index: 679