Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 814 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0514. Min Act: -0.0006

Data Index: 1257381 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0499. Min Act: -0.0006

Data Index: 611734 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0499. Min Act: -0.0006

Data Index: 1294678 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0499. Min Act: -0.0006

Data Index: 180382 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0485. Min Act: -0.0006

Data Index: 342316 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0464. Min Act: -0.0006

Data Index: 24789 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0471. Min Act: -0.0006

Data Index: 1314436 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0472. Min Act: -0.0006

Data Index: 767226 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0478. Min Act: -0.0006

Data Index: 1104104 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0466. Min Act: -0.0006

Data Index: 76822 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0457. Min Act: -0.0006

Data Index: 27581 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0465. Min Act: -0.0006

Data Index: 1262608 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0474. Min Act: -0.0006

Data Index: 3574 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0462. Min Act: -0.0006

Data Index: 456358 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0459. Min Act: -0.0006

Data Index: 415235 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0460. Min Act: -0.0006

Data Index: 409156 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0460. Min Act: -0.0006

Data Index: 483082 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0454. Min Act: -0.0006

Data Index: 301077 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0464. Min Act: -0.0006

Data Index: 822475 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0452. Min Act: -0.0006

Data Index: 574742 (C4 (Web Text))

Max Activating Token Index: 201