Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1228 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0911. Min Range: -1.0911

Max Act: 1.0911. Min Act: -0.0001

Data Index: 81643 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.9460. Min Act: -0.0001

Data Index: 1071394 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.9527. Min Act: -0.0001

Data Index: 1620470 (Python Code)

Max Activating Token Index: 751

Text #3

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.9062. Min Act: -0.0001

Data Index: 730012 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.9367. Min Act: -0.0001

Data Index: 462270 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.9004. Min Act: -0.0001

Data Index: 1512464 (Python Code)

Max Activating Token Index: 474

Text #6

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8898. Min Act: -0.0001

Data Index: 1177617 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8790. Min Act: -0.0001

Data Index: 1180638 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8530. Min Act: -0.0001

Data Index: 1397277 (Python Code)

Max Activating Token Index: 115

Text #9

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8469. Min Act: -0.0001

Data Index: 1340294 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8659. Min Act: -0.0001

Data Index: 777153 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8876. Min Act: -0.0001

Data Index: 165813 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8901. Min Act: -0.0001

Data Index: 474921 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8301. Min Act: -0.0001

Data Index: 182499 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8316. Min Act: -0.0001

Data Index: 1154599 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.9037. Min Act: -0.0001

Data Index: 1002605 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8425. Min Act: -0.0001

Data Index: 571490 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8136. Min Act: -0.0001

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.7435. Min Act: -0.0001

Data Index: 578606 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 1.0911. Min Range: -1.0911

Max Act: 0.8876. Min Act: -0.0001

Data Index: 790258 (C4 (Web Text))

Max Activating Token Index: 904