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

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

Neuron 6019 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1133. Min Range: -1.1133

Max Act: 1.1133. Min Act: -0.0000

Data Index: 1114301 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 1.1133. Min Range: -1.1133

Max Act: 1.0761. Min Act: -0.0000

Data Index: 726434 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 1.1133. Min Range: -1.1133

Max Act: 1.0426. Min Act: -0.0000

Data Index: 712438 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.9379. Min Act: 0.0000

Data Index: 1352993 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1160452 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8855. Min Act: -0.0000

Data Index: 879821 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1347946 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8185. Min Act: -0.0000

Data Index: 317432 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7669. Min Act: -0.0000

Data Index: 760577 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7921. Min Act: -0.0000

Data Index: 167031 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7485. Min Act: -0.0000

Data Index: 744948 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7865. Min Act: 0.0000

Data Index: 665835 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7852. Min Act: -0.0000

Data Index: 390628 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7864. Min Act: 0.0000

Data Index: 1183941 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8113. Min Act: -0.0000

Data Index: 101041 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1435834 (Python Code)

Max Activating Token Index: 545

Text #16

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7867. Min Act: -0.0000

Data Index: 937423 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.6928. Min Act: 0.0001

Data Index: 1107391 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7990. Min Act: -0.0000

Data Index: 180951 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7458. Min Act: -0.0000

Data Index: 112235 (C4 (Web Text))

Max Activating Token Index: 226