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

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

Neuron 2892 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: 0.5526. Min Range: -0.5526

Max Act: 0.5390. Min Act: -0.0000

Data Index: 340410 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.5526. Min Act: -0.0000

Data Index: 192509 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.5394. Min Act: 0.0001

Data Index: 1013498 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.5406. Min Act: 0.0000

Data Index: 806040 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4943. Min Act: -0.0000

Data Index: 630324 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.5027. Min Act: -0.0000

Data Index: 68482 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1062000 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4392. Min Act: -0.0000

Data Index: 647074 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4648. Min Act: -0.0000

Data Index: 474343 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4452. Min Act: -0.0000

Data Index: 981378 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4591. Min Act: -0.0000

Data Index: 633080 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1082726 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1196625 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4513. Min Act: 0.0000

Data Index: 958461 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4488. Min Act: -0.0000

Data Index: 689860 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4458. Min Act: -0.0000

Data Index: 695010 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4552. Min Act: -0.0000

Data Index: 321642 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4300. Min Act: -0.0000

Data Index: 2126 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4322. Min Act: -0.0000

Data Index: 501243 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4281. Min Act: -0.0000

Data Index: 893900 (C4 (Web Text))

Max Activating Token Index: 191