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

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

Neuron 1035 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: 0.9505. Min Range: -0.9505

Max Act: 0.9158. Min Act: -0.0000

Data Index: 493896 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.9041. Min Act: -0.0000

Data Index: 486455 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.9230. Min Act: -0.0001

Data Index: 734898 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8544. Min Act: -0.0000

Data Index: 754999 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.9341. Min Act: -0.0000

Data Index: 994747 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1148521 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.9505. Min Act: -0.0000

Data Index: 204812 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1286988 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8043. Min Act: -0.0001

Data Index: 16972 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8424. Min Act: -0.0000

Data Index: 427634 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8235. Min Act: -0.0001

Data Index: 1251081 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8143. Min Act: -0.0000

Data Index: 275832 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7426. Min Act: -0.0000

Data Index: 476757 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7795. Min Act: -0.0000

Data Index: 656760 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7898. Min Act: -0.0000

Data Index: 284948 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8056. Min Act: -0.0000

Data Index: 83763 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1141167 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7784. Min Act: -0.0000

Data Index: 341152 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1253095 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1144643 (C4 (Web Text))

Max Activating Token Index: 181