Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1551 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.5128. Min Act: -0.0001

Data Index: 28681 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4747. Min Act: -0.0001

Data Index: 1002853 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4720. Min Act: -0.0001

Data Index: 890695 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4547. Min Act: 0.0003

Data Index: 897572 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4711. Min Act: -0.0001

Data Index: 791708 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4501. Min Act: -0.0001

Data Index: 1128888 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4415. Min Act: -0.0001

Data Index: 431602 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4533. Min Act: -0.0000

Data Index: 709562 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4397. Min Act: -0.0001

Data Index: 350833 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4340. Min Act: 0.0002

Data Index: 326668 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4085. Min Act: -0.0001

Data Index: 1201976 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1231489 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3915. Min Act: -0.0001

Data Index: 893370 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3894. Min Act: -0.0001

Data Index: 1255995 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4080. Min Act: -0.0001

Data Index: 843659 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3982. Min Act: 0.0001

Data Index: 430326 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3936. Min Act: -0.0000

Data Index: 634386 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4042. Min Act: -0.0001

Data Index: 1339639 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3913. Min Act: 0.0003

Data Index: 193863 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4126. Min Act: 0.0003

Data Index: 790386 (C4 (Web Text))

Max Activating Token Index: 216