Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1814 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0430. Min Act: -0.0006

Data Index: 399092 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0428. Min Act: -0.0006

Data Index: 162033 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0419. Min Act: -0.0006

Data Index: 1032552 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0425. Min Act: -0.0006

Data Index: 1055150 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0423. Min Act: -0.0006

Data Index: 778515 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0419. Min Act: -0.0006

Data Index: 890870 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0428. Min Act: -0.0006

Data Index: 59836 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0411. Min Act: -0.0006

Data Index: 702774 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0408. Min Act: -0.0006

Data Index: 492573 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0408. Min Act: -0.0006

Data Index: 545638 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0416. Min Act: -0.0006

Data Index: 747592 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0435. Min Act: -0.0006

Data Index: 10087 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0399. Min Act: -0.0006

Data Index: 367137 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0411. Min Act: -0.0006

Data Index: 1122016 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1162944 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0381. Min Act: -0.0006

Data Index: 93359 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0413. Min Act: -0.0006

Data Index: 976353 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0393. Min Act: -0.0006

Data Index: 1127342 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0391. Min Act: -0.0006

Data Index: 503573 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1264671 (C4 (Web Text))

Max Activating Token Index: 316