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

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

Neuron 3199 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: 0.2366. Min Range: -0.2366

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1147247 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.2112. Min Act: -0.0000

Data Index: 870976 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1116087 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1708. Min Act: -0.0000

Data Index: 657038 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1720. Min Act: -0.0000

Data Index: 934075 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1631. Min Act: -0.0000

Data Index: 321090 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1535. Min Act: -0.0000

Data Index: 497220 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1452. Min Act: -0.0000

Data Index: 147733 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1588938 (Python Code)

Max Activating Token Index: 667

Text #9

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1415. Min Act: -0.0000

Data Index: 698610 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1403. Min Act: -0.0000

Data Index: 464327 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1542. Min Act: -0.0000

Data Index: 740177 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1418. Min Act: -0.0000

Data Index: 59323 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1454. Min Act: -0.0000

Data Index: 656195 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1458. Min Act: -0.0000

Data Index: 590242 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1245606 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1462. Min Act: -0.0000

Data Index: 316645 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1298494 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1392. Min Act: -0.0000

Data Index: 78127 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1382. Min Act: -0.0000

Data Index: 422376 (C4 (Web Text))

Max Activating Token Index: 746