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

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

Neuron 4744 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: 3.8035. Min Range: -3.8035

Max Act: 3.8035. Min Act: -0.0001

Data Index: 783324 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.6750. Min Act: -0.0001

Data Index: 873079 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.5016. Min Act: -0.0000

Data Index: 328554 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.0039. Min Act: -0.0000

Data Index: 1027057 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.0394. Min Act: -0.0001

Data Index: 1331276 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.6728. Min Act: -0.0000

Data Index: 711338 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.3648. Min Act: -0.0001

Data Index: 979264 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.3202. Min Act: -0.0001

Data Index: 396093 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.4646. Min Act: -0.0001

Data Index: 399107 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 3.8035. Min Range: -3.8035

Max Act: 2.8950. Min Act: -0.0001

Data Index: 1230518 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.0262. Min Act: -0.0001

Data Index: 521347 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.1635. Min Act: -0.0001

Data Index: 980975 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 3.8035. Min Range: -3.8035

Max Act: 2.9069. Min Act: -0.0001

Data Index: 993803 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.0358. Min Act: -0.0001

Data Index: 832416 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 3.8035. Min Range: -3.8035

Max Act: 3.0003. Min Act: -0.0001

Data Index: 304988 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.8035. Min Range: -3.8035

Max Act: 2.8607. Min Act: -0.0001

Data Index: 1232208 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 3.8035. Min Range: -3.8035

Max Act: 2.6504. Min Act: -0.0001

Data Index: 474606 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 3.8035. Min Range: -3.8035

Max Act: 2.7710. Min Act: -0.0001

Data Index: 1234247 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 3.8035. Min Range: -3.8035

Max Act: 2.9236. Min Act: -0.0001

Data Index: 1103372 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 3.8035. Min Range: -3.8035

Max Act: 2.8568. Min Act: -0.0001

Data Index: 1237346 (C4 (Web Text))

Max Activating Token Index: 31