Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 856 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3574. Min Act: -0.0001

Data Index: 1047060 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3453. Min Act: -0.0001

Data Index: 428212 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3661. Min Act: -0.0001

Data Index: 557347 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3013. Min Act: -0.0001

Data Index: 542345 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2986. Min Act: -0.0001

Data Index: 423388 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2601. Min Act: -0.0001

Data Index: 143440 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2643. Min Act: -0.0001

Data Index: 708561 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3026. Min Act: -0.0001

Data Index: 754738 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3220. Min Act: -0.0001

Data Index: 406206 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2897. Min Act: -0.0001

Data Index: 205520 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2565. Min Act: -0.0001

Data Index: 356027 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2909. Min Act: -0.0001

Data Index: 284221 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2770. Min Act: -0.0001

Data Index: 133820 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2571. Min Act: -0.0001

Data Index: 813419 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2471. Min Act: -0.0001

Data Index: 864087 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2531. Min Act: -0.0001

Data Index: 828339 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2771. Min Act: -0.0001

Data Index: 645162 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2348. Min Act: -0.0001

Data Index: 736784 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2521. Min Act: -0.0001

Data Index: 907203 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2301. Min Act: -0.0001

Data Index: 694018 (C4 (Web Text))

Max Activating Token Index: 848