Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4322 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.9028. Min Act: -0.0001

Data Index: 1148970 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8978. Min Act: -0.0001

Data Index: 831327 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.9729. Min Act: -0.0001

Data Index: 823615 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.9103. Min Act: -0.0001

Data Index: 371598 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7927. Min Act: -0.0001

Data Index: 220396 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8090. Min Act: -0.0001

Data Index: 278658 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8791. Min Act: -0.0001

Data Index: 1277100 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7476. Min Act: -0.0001

Data Index: 1004619 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7446. Min Act: -0.0001

Data Index: 720612 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.6666. Min Act: -0.0001

Data Index: 164418 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7825. Min Act: -0.0001

Data Index: 793501 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7456. Min Act: -0.0001

Data Index: 223479 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7897. Min Act: -0.0001

Data Index: 193308 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7289. Min Act: -0.0001

Data Index: 944314 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7312. Min Act: -0.0001

Data Index: 569314 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7587. Min Act: -0.0001

Data Index: 370888 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.6521. Min Act: -0.0001

Data Index: 1230115 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7906. Min Act: -0.0001

Data Index: 1249761 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7467. Min Act: -0.0001

Data Index: 699172 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8468. Min Act: -0.0001

Data Index: 335302 (C4 (Web Text))

Max Activating Token Index: 576