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

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

Neuron 5478 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.9259. Min Act: -0.0001

Data Index: 599446 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.7015. Min Act: -0.0001

Data Index: 763958 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8846. Min Act: -0.0001

Data Index: 610479 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.7496. Min Act: -0.0001

Data Index: 805329 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.6876. Min Act: -0.0001

Data Index: 408000 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.6012. Min Act: -0.0001

Data Index: 300644 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.5502. Min Act: -0.0001

Data Index: 995453 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.5104. Min Act: -0.0001

Data Index: 840643 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.5809. Min Act: -0.0001

Data Index: 1098307 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.6345. Min Act: -0.0001

Data Index: 1128514 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.5482. Min Act: -0.0001

Data Index: 1239506 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.4311. Min Act: -0.0001

Data Index: 1113483 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.4885. Min Act: -0.0001

Data Index: 801138 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.3157. Min Act: -0.0001

Data Index: 778876 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.3819. Min Act: -0.0001

Data Index: 808927 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.4337. Min Act: -0.0001

Data Index: 59476 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.5013. Min Act: -0.0001

Data Index: 1178804 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.3973. Min Act: -0.0001

Data Index: 130386 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.3910. Min Act: -0.0001

Data Index: 237075 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.4613. Min Act: -0.0001

Data Index: 451186 (C4 (Web Text))

Max Activating Token Index: 692