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

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

Neuron 195 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0005

Data Index: 1067951 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0645. Min Act: -0.0005

Data Index: 1028221 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0582. Min Act: -0.0005

Data Index: 633822 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0525. Min Act: -0.0005

Data Index: 851407 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0527. Min Act: -0.0005

Data Index: 1281269 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0520. Min Act: -0.0005

Data Index: 264238 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0507. Min Act: -0.0005

Data Index: 1137901 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0502. Min Act: -0.0006

Data Index: 234504 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0496. Min Act: -0.0005

Data Index: 423522 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0493. Min Act: -0.0005

Data Index: 185777 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0477. Min Act: -0.0005

Data Index: 1325083 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0496. Min Act: -0.0005

Data Index: 712119 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0476. Min Act: -0.0005

Data Index: 822692 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0480. Min Act: -0.0005

Data Index: 406070 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0472. Min Act: -0.0005

Data Index: 1056781 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0472. Min Act: -0.0005

Data Index: 999555 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0471. Min Act: -0.0005

Data Index: 220800 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0480. Min Act: -0.0005

Data Index: 535955 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0457. Min Act: -0.0005

Data Index: 1247821 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0454. Min Act: -0.0005

Data Index: 1338040 (C4 (Web Text))

Max Activating Token Index: 30