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

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

Neuron 1368 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8494. Min Act: -0.0001

Data Index: 313753 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8666. Min Act: -0.0001

Data Index: 392090 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8446. Min Act: -0.0001

Data Index: 154581 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8364. Min Act: -0.0001

Data Index: 618134 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8138. Min Act: -0.0001

Data Index: 39879 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8141. Min Act: -0.0001

Data Index: 211018 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8069. Min Act: -0.0001

Data Index: 223599 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8077. Min Act: -0.0001

Data Index: 1137177 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8026. Min Act: -0.0001

Data Index: 115633 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8109. Min Act: -0.0001

Data Index: 73221 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8075. Min Act: -0.0001

Data Index: 1235487 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8066. Min Act: -0.0001

Data Index: 562391 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.7947. Min Act: -0.0001

Data Index: 529552 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8255. Min Act: -0.0001

Data Index: 502012 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.7930. Min Act: -0.0001

Data Index: 971117 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.7585. Min Act: -0.0001

Data Index: 802741 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.7672. Min Act: -0.0001

Data Index: 1290540 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.7991. Min Act: -0.0001

Data Index: 520601 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.7867. Min Act: -0.0001

Data Index: 858146 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8029. Min Act: -0.0001

Data Index: 498957 (C4 (Web Text))

Max Activating Token Index: 897