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

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

Neuron 2949 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.8073. Min Act: -0.0000

Data Index: 629642 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7685. Min Act: -0.0000

Data Index: 455205 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7031. Min Act: -0.0000

Data Index: 827562 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5886. Min Act: -0.0000

Data Index: 892392 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5836. Min Act: -0.0000

Data Index: 380595 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5683. Min Act: -0.0000

Data Index: 293027 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5101. Min Act: -0.0000

Data Index: 402112 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5625. Min Act: -0.0000

Data Index: 757367 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5145. Min Act: -0.0000

Data Index: 980448 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1243148 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5244. Min Act: -0.0000

Data Index: 760569 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5026. Min Act: -0.0000

Data Index: 194783 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4457. Min Act: -0.0000

Data Index: 903836 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4320. Min Act: -0.0000

Data Index: 830196 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4419. Min Act: -0.0000

Data Index: 107330 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4315. Min Act: -0.0000

Data Index: 842607 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4406. Min Act: -0.0000

Data Index: 559058 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.3902. Min Act: -0.0000

Data Index: 668612 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4561. Min Act: -0.0000

Data Index: 644785 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4369. Min Act: -0.0000

Data Index: 438514 (C4 (Web Text))

Max Activating Token Index: 658