Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 213 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.7539. Min Act: -0.0000

Data Index: 712398 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5816. Min Act: -0.0000

Data Index: 12266 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.7447. Min Act: -0.0000

Data Index: 851864 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.4298. Min Act: -0.0000

Data Index: 1107882 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.4349. Min Act: -0.0000

Data Index: 923993 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5975. Min Act: -0.0000

Data Index: 520751 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5946. Min Act: -0.0000

Data Index: 99807 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5709. Min Act: -0.0000

Data Index: 1128447 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5835. Min Act: -0.0000

Data Index: 450416 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.4143. Min Act: -0.0000

Data Index: 1037970 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.4147. Min Act: -0.0000

Data Index: 1348933 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5506. Min Act: -0.0000

Data Index: 424216 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5553. Min Act: -0.0000

Data Index: 560544 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5530. Min Act: -0.0000

Data Index: 806606 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5204. Min Act: -0.0000

Data Index: 272428 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.5214. Min Act: -0.0000

Data Index: 1151601 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.3470. Min Act: -0.0000

Data Index: 164179 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.6446. Min Act: -0.0000

Data Index: 1004127 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.4991. Min Act: -0.0000

Data Index: 801155 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 3.7539. Min Range: -3.7539

Max Act: 3.4676. Min Act: -0.0000

Data Index: 1036213 (C4 (Web Text))

Max Activating Token Index: 716