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

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

Neuron 568 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2041. Min Range: -2.2041

Max Act: 2.2041. Min Act: -0.0000

Data Index: 15504 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 2.2041. Min Range: -2.2041

Max Act: 2.0886. Min Act: -0.0000

Data Index: 1163897 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 2.2041. Min Range: -2.2041

Max Act: 2.0956. Min Act: -0.0000

Data Index: 144769 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 2.2041. Min Range: -2.2041

Max Act: 2.0232. Min Act: -0.0000

Data Index: 846117 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 2.2041. Min Range: -2.2041

Max Act: 2.0888. Min Act: -0.0000

Data Index: 318041 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 2.2041. Min Range: -2.2041

Max Act: 2.0417. Min Act: -0.0000

Data Index: 427025 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 2.2041. Min Range: -2.2041

Max Act: 2.0100. Min Act: -0.0000

Data Index: 1183442 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 2.2041. Min Range: -2.2041

Max Act: 2.0900. Min Act: -0.0000

Data Index: 658454 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.8675. Min Act: -0.0000

Data Index: 1238403 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.9507. Min Act: -0.0000

Data Index: 583834 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.9274. Min Act: -0.0000

Data Index: 247319 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.9031. Min Act: -0.0000

Data Index: 79363 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.8726. Min Act: -0.0000

Data Index: 885878 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.8835. Min Act: -0.0000

Data Index: 1197475 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.8973. Min Act: -0.0000

Data Index: 757292 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.8454. Min Act: -0.0000

Data Index: 377574 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.9427. Min Act: -0.0000

Data Index: 1006167 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.8443. Min Act: -0.0000

Data Index: 746376 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.7455. Min Act: -0.0000

Data Index: 220037 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 2.2041. Min Range: -2.2041

Max Act: 1.9003. Min Act: -0.0000

Data Index: 638403 (C4 (Web Text))

Max Activating Token Index: 1008