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

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

Neuron 1968 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: 0.0507. Min Range: -0.0507

Max Act: 0.0483. Min Act: -0.0006

Data Index: 577834 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0482. Min Act: -0.0006

Data Index: 284397 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0493. Min Act: -0.0006

Data Index: 261316 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0492. Min Act: -0.0006

Data Index: 373664 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0452. Min Act: -0.0006

Data Index: 921825 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0006

Data Index: 1189066 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0485. Min Act: -0.0006

Data Index: 1249028 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0447. Min Act: -0.0006

Data Index: 1160045 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0462. Min Act: -0.0006

Data Index: 610547 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0416. Min Act: -0.0006

Data Index: 150780 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0477. Min Act: -0.0006

Data Index: 1305785 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0468. Min Act: -0.0006

Data Index: 92151 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0468. Min Act: -0.0006

Data Index: 311250 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0459. Min Act: -0.0006

Data Index: 697496 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0427. Min Act: -0.0006

Data Index: 117643 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0459. Min Act: -0.0006

Data Index: 997811 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0451. Min Act: -0.0006

Data Index: 336542 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0429. Min Act: -0.0006

Data Index: 92978 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0446. Min Act: -0.0006

Data Index: 1350039 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0448. Min Act: -0.0006

Data Index: 981432 (C4 (Web Text))

Max Activating Token Index: 400