Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2490 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.7861. Min Act: -0.0001

Data Index: 1336280 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.8141. Min Act: -0.0001

Data Index: 244416 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.5110. Min Act: -0.0001

Data Index: 1181090 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.6643. Min Act: -0.0001

Data Index: 48041 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.5711. Min Act: -0.0001

Data Index: 170821 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.6075. Min Act: -0.0001

Data Index: 474844 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.6028. Min Act: -0.0001

Data Index: 130873 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.5198. Min Act: -0.0001

Data Index: 775120 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.5118. Min Act: -0.0001

Data Index: 258255 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.5992. Min Act: -0.0001

Data Index: 26976 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.6183. Min Act: -0.0001

Data Index: 83485 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.6050. Min Act: -0.0001

Data Index: 517388 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.4890. Min Act: -0.0001

Data Index: 727872 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.7578. Min Act: -0.0001

Data Index: 874930 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.4045. Min Act: -0.0001

Data Index: 431827 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.3151. Min Act: -0.0001

Data Index: 745292 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.4737. Min Act: -0.0001

Data Index: 1171953 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.3737. Min Act: -0.0001

Data Index: 271738 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.5440. Min Act: -0.0001

Data Index: 213034 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 1.8141. Min Range: -1.8141

Max Act: 1.4528. Min Act: -0.0001

Data Index: 1014944 (C4 (Web Text))

Max Activating Token Index: 886