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

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

Neuron 1176 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: 0.0518. Min Range: -0.0518

Max Act: 0.0486. Min Act: -0.0006

Data Index: 386470 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0471. Min Act: -0.0006

Data Index: 212057 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0518. Min Act: -0.0006

Data Index: 402673 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0509. Min Act: -0.0006

Data Index: 1239120 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0444. Min Act: -0.0006

Data Index: 625104 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0429. Min Act: -0.0006

Data Index: 1173379 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0454. Min Act: -0.0006

Data Index: 790732 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0435. Min Act: -0.0006

Data Index: 1139254 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0490. Min Act: -0.0006

Data Index: 358832 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0431. Min Act: -0.0006

Data Index: 678559 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0452. Min Act: -0.0006

Data Index: 1111962 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0444. Min Act: -0.0006

Data Index: 938182 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0421. Min Act: -0.0006

Data Index: 620943 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0457. Min Act: -0.0006

Data Index: 1160951 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0477. Min Act: -0.0006

Data Index: 184496 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0419. Min Act: -0.0006

Data Index: 504788 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0419. Min Act: -0.0006

Data Index: 224188 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0471. Min Act: -0.0006

Data Index: 1304882 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0449. Min Act: -0.0006

Data Index: 800203 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0427. Min Act: -0.0006

Data Index: 799564 (C4 (Web Text))

Max Activating Token Index: 20