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

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

Neuron 1185 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6667. Min Act: -0.0000

Data Index: 488114 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6279. Min Act: -0.0000

Data Index: 148523 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1244704 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1005633 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5320. Min Act: -0.0000

Data Index: 548876 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4632. Min Act: -0.0000

Data Index: 637945 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4389. Min Act: -0.0000

Data Index: 421500 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4305. Min Act: -0.0000

Data Index: 72772 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4576. Min Act: -0.0000

Data Index: 77364 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4257. Min Act: -0.0000

Data Index: 647263 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1073232 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4188. Min Act: -0.0000

Data Index: 735174 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4308. Min Act: -0.0000

Data Index: 216374 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1331389 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4213. Min Act: -0.0000

Data Index: 307273 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1094915 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4145. Min Act: -0.0000

Data Index: 454417 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1357186 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4249. Min Act: -0.0000

Data Index: 632975 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4198. Min Act: -0.0000

Data Index: 21126 (C4 (Web Text))

Max Activating Token Index: 484