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

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

Neuron 480 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: 2.9933. Min Range: -2.9933

Max Act: 2.9417. Min Act: -0.0000

Data Index: 1107898 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.9668. Min Act: -0.0000

Data Index: 575854 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.7462. Min Act: -0.0000

Data Index: 671952 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.9933. Min Act: -0.0000

Data Index: 1013395 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.8796. Min Act: -0.0000

Data Index: 617999 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.7556. Min Act: -0.0000

Data Index: 1349492 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.7253. Min Act: -0.0000

Data Index: 414959 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.6870. Min Act: -0.0000

Data Index: 1281566 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.5613. Min Act: -0.0000

Data Index: 614659 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.9338. Min Act: -0.0000

Data Index: 557926 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.6127. Min Act: -0.0000

Data Index: 280474 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.4974. Min Act: -0.0000

Data Index: 415881 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.5804. Min Act: -0.0000

Data Index: 114118 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.5706. Min Act: -0.0000

Data Index: 68646 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.5783. Min Act: -0.0000

Data Index: 353911 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.3233. Min Act: -0.0000

Data Index: 1063525 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.2981. Min Act: -0.0000

Data Index: 1063191 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.5230. Min Act: -0.0000

Data Index: 103810 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.5482. Min Act: -0.0000

Data Index: 1184753 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.4120. Min Act: -0.0000

Data Index: 602401 (C4 (Web Text))

Max Activating Token Index: 118