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

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

Neuron 46 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: 1.0279. Min Range: -1.0279

Max Act: 1.0279. Min Act: -0.0000

Data Index: 856367 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8401. Min Act: -0.0000

Data Index: 806319 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8677. Min Act: -0.0000

Data Index: 238041 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8644. Min Act: -0.0000

Data Index: 988728 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1274016 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1120362 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1012654 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7987. Min Act: -0.0000

Data Index: 437473 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1027159 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7833. Min Act: -0.0000

Data Index: 581568 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8101. Min Act: -0.0000

Data Index: 992097 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7985. Min Act: -0.0000

Data Index: 891569 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1044201 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7916. Min Act: -0.0000

Data Index: 511758 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1156391 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1317120 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1232614 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7523. Min Act: -0.0000

Data Index: 594243 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1229807 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7086. Min Act: -0.0000

Data Index: 362411 (C4 (Web Text))

Max Activating Token Index: 965