Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3486 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0215. Min Act: -0.0000

Data Index: 527864 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0121. Min Act: -0.0000

Data Index: 1072648 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0112. Min Act: -0.0000

Data Index: 100763 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0108. Min Act: -0.0000

Data Index: 1182690 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0107. Min Act: -0.0000

Data Index: 850589 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0095. Min Act: -0.0000

Data Index: 712521 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0098. Min Act: -0.0000

Data Index: 24216 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0095. Min Act: -0.0000

Data Index: 353015 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0097. Min Act: -0.0000

Data Index: 296028 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0097. Min Act: -0.0000

Data Index: 745622 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0090. Min Act: -0.0000

Data Index: 568495 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0094. Min Act: -0.0000

Data Index: 122616 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0093. Min Act: -0.0000

Data Index: 331223 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0092. Min Act: -0.0000

Data Index: 1384531 (Python Code)

Max Activating Token Index: 703

Text #14

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0090. Min Act: -0.0000

Data Index: 277249 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0089. Min Act: -0.0000

Data Index: 1270957 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0087. Min Act: -0.0000

Data Index: 631562 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0087. Min Act: -0.0000

Data Index: 314658 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0093. Min Act: -0.0000

Data Index: 100731 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0085. Min Act: -0.0000

Data Index: 649193 (C4 (Web Text))

Max Activating Token Index: 430