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

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

Neuron 4045 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1208649 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1080477 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9438. Min Act: -0.0000

Data Index: 767724 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9263. Min Act: -0.0000

Data Index: 581545 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1156849 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8923. Min Act: -0.0000

Data Index: 149773 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1090157 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1145470 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1171423 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8483. Min Act: -0.0000

Data Index: 597480 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1099470 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1164716 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8014. Min Act: -0.0000

Data Index: 446831 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1320659 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7678. Min Act: -0.0000

Data Index: 597178 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8161. Min Act: -0.0000

Data Index: 626821 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7596. Min Act: -0.0000

Data Index: 591158 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1311821 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1200666 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1073292 (C4 (Web Text))

Max Activating Token Index: 502