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

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

Neuron 1133 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1117345 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1203729 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1115004 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7380. Min Act: -0.0000

Data Index: 756388 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6845. Min Act: -0.0000

Data Index: 945262 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6789. Min Act: -0.0000

Data Index: 590743 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6939. Min Act: -0.0000

Data Index: 897695 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1008613 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1110722 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1184051 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1207299 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5304. Min Act: -0.0000

Data Index: 533292 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5394. Min Act: -0.0000

Data Index: 544761 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1194750 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1236954 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5223. Min Act: -0.0000

Data Index: 545305 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5309. Min Act: -0.0000

Data Index: 990468 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5698. Min Act: -0.0000

Data Index: 875077 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.4885. Min Act: -0.0000

Data Index: 202100 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.4687. Min Act: -0.0000

Data Index: 724551 (C4 (Web Text))

Max Activating Token Index: 510