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

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

Neuron 3436 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1761. Min Act: -0.0000

Data Index: 209561 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1646. Min Act: -0.0000

Data Index: 980042 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1587. Min Act: -0.0000

Data Index: 267967 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1136243 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1603. Min Act: -0.0000

Data Index: 890222 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1537. Min Act: -0.0000

Data Index: 86285 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1537. Min Act: -0.0000

Data Index: 82580 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1444. Min Act: -0.0000

Data Index: 705303 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1432. Min Act: -0.0000

Data Index: 998294 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1218563 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1323. Min Act: -0.0000

Data Index: 268472 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1314. Min Act: -0.0000

Data Index: 581840 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1309. Min Act: -0.0000

Data Index: 920802 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1052887 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1144. Min Act: -0.0000

Data Index: 187130 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1172. Min Act: -0.0001

Data Index: 535208 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1500649 (Python Code)

Max Activating Token Index: 862

Text #17

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1121. Min Act: -0.0001

Data Index: 238822 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1172. Min Act: -0.0001

Data Index: 475383 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1126. Min Act: -0.0001

Data Index: 388121 (C4 (Web Text))

Max Activating Token Index: 278