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

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

Neuron 4425 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5971. Min Act: -0.0001

Data Index: 510050 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4816. Min Act: -0.0001

Data Index: 694473 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5533. Min Act: -0.0000

Data Index: 330087 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4415. Min Act: -0.0000

Data Index: 126864 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4200. Min Act: -0.0001

Data Index: 640989 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1192434 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4075. Min Act: -0.0001

Data Index: 129769 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4184. Min Act: -0.0001

Data Index: 51129 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4106. Min Act: -0.0000

Data Index: 532898 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.3996. Min Act: -0.0001

Data Index: 1294646 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4237. Min Act: -0.0001

Data Index: 1168459 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.3942. Min Act: -0.0001

Data Index: 75593 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.3576. Min Act: -0.0001

Data Index: 713176 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4247. Min Act: -0.0000

Data Index: 983972 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1062389 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4097. Min Act: -0.0001

Data Index: 736217 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4012. Min Act: -0.0001

Data Index: 280837 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1073607 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1132539 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.3335. Min Act: -0.0001

Data Index: 1339669 (C4 (Web Text))

Max Activating Token Index: 557