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

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

Neuron 2228 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: 0.5461. Min Range: -0.5461

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1133541 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1229099 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4724. Min Act: -0.0000

Data Index: 367185 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4451. Min Act: -0.0000

Data Index: 375632 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1314053 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1032172 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4372. Min Act: -0.0000

Data Index: 444343 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4812. Min Act: -0.0000

Data Index: 165007 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1259390 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4079. Min Act: 0.0001

Data Index: 198379 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1005135 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4060. Min Act: 0.0000

Data Index: 641849 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1164999 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4062. Min Act: 0.0000

Data Index: 214644 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3877. Min Act: -0.0000

Data Index: 837067 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4005. Min Act: -0.0000

Data Index: 485723 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3861. Min Act: -0.0000

Data Index: 813435 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1146049 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3904. Min Act: -0.0000

Data Index: 812743 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3853. Min Act: 0.0000

Data Index: 1006089 (C4 (Web Text))

Max Activating Token Index: 972