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

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

Neuron 3022 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6881. Min Act: -0.0001

Data Index: 632595 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5858. Min Act: -0.0001

Data Index: 141740 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6208. Min Act: -0.0001

Data Index: 1103833 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5520. Min Act: -0.0002

Data Index: 422502 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5367. Min Act: -0.0001

Data Index: 806726 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4879. Min Act: -0.0002

Data Index: 163468 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5205. Min Act: -0.0002

Data Index: 119214 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4588. Min Act: -0.0002

Data Index: 397653 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4387. Min Act: -0.0001

Data Index: 823684 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4214. Min Act: -0.0002

Data Index: 997068 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4633. Min Act: -0.0001

Data Index: 471596 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4344. Min Act: -0.0001

Data Index: 1320693 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4563. Min Act: -0.0001

Data Index: 350376 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4521. Min Act: -0.0002

Data Index: 1288423 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4452. Min Act: -0.0002

Data Index: 71481 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4459. Min Act: -0.0002

Data Index: 444463 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4479. Min Act: -0.0002

Data Index: 369752 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4465. Min Act: -0.0002

Data Index: 377752 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4176. Min Act: -0.0002

Data Index: 1066512 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4264. Min Act: -0.0002

Data Index: 498932 (C4 (Web Text))

Max Activating Token Index: 477