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

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

Neuron 3633 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5146. Min Range: -5.5146

Max Act: 5.5146. Min Act: -0.0001

Data Index: 581137 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 5.5146. Min Range: -5.5146

Max Act: 5.0956. Min Act: -0.0001

Data Index: 830917 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.4059. Min Act: -0.0001

Data Index: 142017 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.7578. Min Act: -0.0001

Data Index: 1081209 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.4209. Min Act: -0.0001

Data Index: 392242 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.4301. Min Act: -0.0001

Data Index: 240485 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.5439. Min Act: -0.0001

Data Index: 1182286 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.6684. Min Act: -0.0001

Data Index: 155287 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.1441. Min Act: -0.0001

Data Index: 862690 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.8575. Min Act: -0.0001

Data Index: 466614 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.4404. Min Act: -0.0001

Data Index: 1213941 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.2069. Min Act: -0.0000

Data Index: 658326 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.1403. Min Act: -0.0001

Data Index: 908763 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 5.5146. Min Range: -5.5146

Max Act: 3.9007. Min Act: -0.0001

Data Index: 148960 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 5.5146. Min Range: -5.5146

Max Act: 3.8987. Min Act: -0.0000

Data Index: 719261 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.2098. Min Act: -0.0001

Data Index: 229949 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 5.5146. Min Range: -5.5146

Max Act: 3.5792. Min Act: -0.0001

Data Index: 396057 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 5.5146. Min Range: -5.5146

Max Act: 4.0456. Min Act: -0.0001

Data Index: 239870 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 5.5146. Min Range: -5.5146

Max Act: 3.9830. Min Act: -0.0001

Data Index: 332973 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 5.5146. Min Range: -5.5146

Max Act: 3.9793. Min Act: -0.0001

Data Index: 1136120 (C4 (Web Text))

Max Activating Token Index: 783