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

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

Neuron 1631 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.6700. Min Act: -0.0000

Data Index: 106421 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.6404. Min Act: -0.0000

Data Index: 307416 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5684. Min Act: -0.0000

Data Index: 931828 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5885. Min Act: -0.0000

Data Index: 816368 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5421. Min Act: -0.0000

Data Index: 448832 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5144. Min Act: -0.0000

Data Index: 80793 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1022602 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1057947 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5070. Min Act: -0.0000

Data Index: 97584 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5044. Min Act: -0.0000

Data Index: 37527 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4897. Min Act: -0.0000

Data Index: 726750 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1013839 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1226099 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4641. Min Act: -0.0000

Data Index: 619526 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4805. Min Act: -0.0000

Data Index: 850526 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4709. Min Act: -0.0000

Data Index: 347449 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4575. Min Act: -0.0000

Data Index: 580633 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4561. Min Act: -0.0000

Data Index: 985427 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1126302 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4526. Min Act: -0.0000

Data Index: 485455 (C4 (Web Text))

Max Activating Token Index: 705