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

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

Neuron 2191 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.7771. Min Act: -0.0000

Data Index: 104403 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1079771 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6436. Min Act: -0.0000

Data Index: 102548 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6313. Min Act: -0.0000

Data Index: 177786 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.6226. Min Act: -0.0000

Data Index: 507375 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1241511 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.5587. Min Act: -0.0000

Data Index: 422752 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.5618. Min Act: -0.0000

Data Index: 972920 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.5596. Min Act: -0.0000

Data Index: 193901 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1348348 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.5149. Min Act: -0.0000

Data Index: 59080 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.5171. Min Act: -0.0000

Data Index: 190137 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.5310. Min Act: -0.0000

Data Index: 203594 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1355622 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.4956. Min Act: -0.0000

Data Index: 930589 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.4638. Min Act: -0.0000

Data Index: 805496 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1314377 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.5084. Min Act: -0.0000

Data Index: 849427 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.4903. Min Act: -0.0000

Data Index: 751241 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.7771. Min Range: -0.7771

Max Act: 0.4805. Min Act: -0.0000

Data Index: 700565 (C4 (Web Text))

Max Activating Token Index: 492