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

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

Neuron 5580 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3901. Min Range: -1.3901

Max Act: 1.3901. Min Act: -0.0000

Data Index: 89963 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 1.3901. Min Range: -1.3901

Max Act: 1.2805. Min Act: -0.0000

Data Index: 623421 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 1.3901. Min Range: -1.3901

Max Act: 1.0825. Min Act: -0.0000

Data Index: 230350 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 1.3901. Min Range: -1.3901

Max Act: 1.0004. Min Act: -0.0000

Data Index: 770556 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.9358. Min Act: -0.0000

Data Index: 515572 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1247096 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1285376 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.9125. Min Act: -0.0000

Data Index: 166743 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.9226. Min Act: -0.0000

Data Index: 372995 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1291373 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1278814 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.9498. Min Act: -0.0000

Data Index: 581730 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.9081. Min Act: -0.0000

Data Index: 19296 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.8758. Min Act: -0.0000

Data Index: 375297 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1171814 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.7759. Min Act: -0.0000

Data Index: 597632 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1000924 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.8125. Min Act: -0.0000

Data Index: 171131 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.8449. Min Act: -0.0000

Data Index: 452815 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 1.3901. Min Range: -1.3901

Max Act: 0.7885. Min Act: -0.0000

Data Index: 650741 (C4 (Web Text))

Max Activating Token Index: 101