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

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

Neuron 3719 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: 1.1210. Min Range: -1.1210

Max Act: 1.1210. Min Act: -0.0001

Data Index: 212599 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9883. Min Act: -0.0001

Data Index: 519455 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9069. Min Act: -0.0001

Data Index: 273124 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9445. Min Act: -0.0001

Data Index: 733279 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8861. Min Act: -0.0001

Data Index: 1494766 (Python Code)

Max Activating Token Index: 552

Text #5

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9490. Min Act: -0.0001

Data Index: 1164551 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9219. Min Act: -0.0001

Data Index: 798548 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1107797 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8748. Min Act: -0.0001

Data Index: 1643154 (Python Code)

Max Activating Token Index: 730

Text #9

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8914. Min Act: -0.0001

Data Index: 1581022 (Python Code)

Max Activating Token Index: 625

Text #10

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8698. Min Act: -0.0001

Data Index: 724471 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8331. Min Act: -0.0001

Data Index: 825340 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8608. Min Act: -0.0001

Data Index: 1372425 (Python Code)

Max Activating Token Index: 417

Text #13

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8365. Min Act: -0.0001

Data Index: 1236246 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8284. Min Act: -0.0001

Data Index: 1096855 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8499. Min Act: -0.0001

Data Index: 506252 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8367. Min Act: -0.0001

Data Index: 554693 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7830. Min Act: -0.0001

Data Index: 1529104 (Python Code)

Max Activating Token Index: 570

Text #18

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8196. Min Act: -0.0001

Data Index: 259969 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8495. Min Act: -0.0001

Data Index: 1189045 (C4 (Web Text))

Max Activating Token Index: 639